Most Influential AAAI Papers (2024-09)
The AAAI Conference on Artificial Intelligence (AAAI) is one of the top artificial intelligence conferences in the world. Paper Digest Team analyzes all papers published on AAAI in the past years, and presents the 15 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2024-09)
To search or review papers within AAAI related to a specific topic, please use the search by venue (AAAI) and review by venue (AAAI) services. To browse the most productive AAAI authors by year ranked by #papers accepted, here are the most productive AAAI authors grouped by year.
This list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that empowers you to write, review, get answers and more.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Most Influential AAAI Papers (2024-09)
| Year | Rank | Paper | Author(s) |
|---|---|---|---|
| 2024 | 1 | T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, relying solely on text prompts cannot fully take advantage of the knowledge learned by the model, especially when flexible and accurate controlling (e.g., structure and color) is needed. In this paper, we aim to “dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly. |
CHONG MOU et. al. |
| 2024 | 2 | Graph of Thoughts: Solving Elaborate Problems with Large Language Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). |
MACIEJ BESTA et. al. |
| 2024 | 3 | Preference Ranking Optimization for Human Alignment IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Preference Ranking Optimization (PRO) as an efficient SFT algorithm to directly fine-tune LLMs for human alignment. |
FEIFAN SONG et. al. |
| 2024 | 4 | Benchmarking Large Language Models in Retrieval-Augmented Generation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models. |
Jiawei Chen; Hongyu Lin; Xianpei Han; Le Sun; |
| 2024 | 5 | From Statistical Relational to Neuro-Symbolic Artificial Intelligence IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our recent work, we provided an introduction to NeSy by drawing several parallels to another field that has a rich tradition in integrating learning and reasoning, namely Statistical Relational Artificial Intelligence (StarAI). |
Giuseppe Marra; |
| 2024 | 6 | Follow Your Pose: Pose-Guided Text-to-Video Generation Using Pose-Free Videos IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we design a novel two-stage training scheme that can utilize easily obtained datasets (i.e., image pose pair and pose-free video) and the pre-trained text-to-image (T2I) model to obtain the pose-controllable character videos. |
YUE MA et. al. |
| 2024 | 7 | ExpeL: LLM Agents Are Experiential Learners IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This scenario emphasizes the growing need for new methodologies that allow learning from agent experiences without requiring parametric updates. To address these problems, we introduce the Experiential Learning (ExpeL) agent. |
ANDREW ZHAO et. al. |
| 2024 | 8 | Detecting and Preventing Hallucinations in Large Vision Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that even the current state-of-the-art LVLMs (InstructBLIP) still contain a staggering 30 percent of the hallucinatory text in the form of non-existent objects, unfaithful descriptions, and inaccurate relationships. To address this, we introduce M-HalDetect, a Multimodal Hallucination Detection Dataset that can be used to train and benchmark models for hallucination detection and prevention. |
Anisha Gunjal; Jihan Yin; Erhan Bas; |
| 2024 | 8 | MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, we discovered that simply combining these two models resulted in subpar performance. To effectively integrate these two cutting-edge techniques for the Medical image segmentation, we propose a novel Transformer-based Diffusion framework, called MedSegDiff-V2. |
JUNDE WU et. al. |
| 2024 | 9 | Visual Adversarial Examples Jailbreak Aligned Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As an illustration, we present a case study in which we exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. |
XIANGYU QI et. al. |
| 2024 | 10 | PMET: Precise Model Editing in A Transformer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This implies that MHSA weights do not require updating when new knowledge is introduced. Based on above findings, we introduce PMET, which simultaneously optimizes Transformer Component (TC, namely MHSA and FFN) hidden states, while only using the optimized TC hidden states of FFN to precisely update FFN weights. |
XIAOPENG LI et. al. |
| 2024 | 11 | Generalized Planning in PDDL Domains with Pretrained Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We evaluate this approach in seven PDDL domains and compare it to four ablations and four baselines. |
TOM SILVER et. al. |
| 2024 | 12 | NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). |
Gengze Zhou; Yicong Hong; Qi Wu; |
| 2024 | 13 | BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To improve upon them, the present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. |
WENBO HU et. al. |
| 2024 | 14 | NuScenes-QA: A Multi-Modal Visual Question Answering Benchmark for Autonomous Driving Scenario IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. |
Tianwen Qian; Jingjing Chen; Linhai Zhuo; Yang Jiao; Yu-Gang Jiang; |
| 2024 | 15 | Task Contamination: Language Models May Not Be Few-Shot Anymore IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. |
Changmao Li; Jeffrey Flanigan; |
| 2023 | 1 | Are Transformers Effective for Time Series Forecasting? IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While employing positional encoding and using tokens to embed sub-series in Transformers facilitate preserving some ordering information, the nature of the permutation-invariant self-attention mechanism inevitably results in temporal information loss. To validate our claim, we introduce a set of embarrassingly simple one-layer linear models named LTSF-Linear for comparison. |
Ailing Zeng; Muxi Chen; Lei Zhang; Qiang Xu; |
| 2023 | 2 | BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird’s-Eye-View~(BEV) 3D object detection. |
YINHAO LI et. al. |
| 2023 | 3 | Exploring CLIP for Assessing The Look and Feel of Images IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we go beyond the conventional paradigms by exploring the rich visual language prior encapsulated in Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images without explicit task-specific training. |
Jianyi Wang; Kelvin C.K. Chan; Chen Change Loy; |
| 2023 | 4 | TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. |
MINGHAO LI et. al. |
| 2023 | 5 | PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper explores a better prediction target for BERT pre-training of vision transformers. |
XIAOYI DONG et. al. |
| 2023 | 6 | A Holistic Approach to Undesired Content Detection in The Real World IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a holistic approach to building a robust and useful natural language classification system for real-world content moderation. |
TODOR MARKOV et. al. |
| 2023 | 7 | Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. |
TAO WANG et. al. |
| 2023 | 8 | PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a novel Propagation Delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. |
Jiawei Jiang; Chengkai Han; Wayne Xin Zhao; Jingyuan Wang; |
| 2023 | 9 | FairFed: Enabling Group Fairness in Federated Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by the importance and challenges of group fairness in federated learning, in this work, we propose FairFed, a novel algorithm for fairness-aware aggregation to enhance group fairness in federated learning. |
Yahya H. Ezzeldin; Shen Yan; Chaoyang He; Emilio Ferrara; A. Salman Avestimehr; |
| 2023 | 10 | Toward A Perspectivist Turn in Ground Truthing for Predictive Computing IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The annotation process is often performed in terms of a majority vote, however this has been proved to be often problematic by recent evaluation studies. In this article, we describe and advocate for a different paradigm, which we call perspectivism: this counters the removal of disagreement and, consequently, the assumption of correctness of traditionally aggregated gold-standard datasets, and proposes the adoption of methods that preserve divergence of opinions and integrate multiple perspectives in the ground truthing process of ML development. |
Federico Cabitza; Andrea Campagner; Valerio Basile; |
| 2023 | 11 | RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a ranking-enhanced encoding and skeleton-aware decoding framework to decouple the schema linking and the skeleton parsing. |
Haoyang Li; Jing Zhang; Cuiping Li; Hong Chen; |
| 2023 | 12 | FedALA: Adaptive Local Aggregation for Personalized Federated Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. |
JIANQING ZHANG et. al. |
| 2023 | 13 | On The Effectiveness of Parameter-Efficient Fine-Tuning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How to choose the tunable parameters? In this paper, we first categorize the existing methods into random approaches, rule-based approaches, and projection-based approaches based on how they choose which parameters to tune. |
ZIHAO FU et. al. |
| 2023 | 14 | Mean-Shifted Contrastive Loss for Anomaly Detection IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We take the approach of transferring representations pre-trained on external datasets for anomaly detection. |
Tal Reiss; Yedid Hoshen; |
| 2023 | 15 | Repair Is Nearly Generation: Multilingual Program Repair with LLMs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce RING, a multilingual repair engine powered by a large language model trained on code (LLMC) such as Codex. |
HARSHIT JOSHI et. al. |
| 2022 | 1 | UCTransNet: Rethinking The Skip Connections in U-Net from A Channel-Wise Perspective with Transformer IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. |
Haonan Wang; Peng Cao; Jiaqi Wang; Osmar R. Zaiane; |
| 2022 | 2 | SplitFed: When Federated Learning Meets Split Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness. |
Chandra Thapa; Pathum Chamikara Mahawaga Arachchige; Seyit Camtepe; Lichao Sun; |
| 2022 | 3 | TS2Vec: Towards Universal Representation of Time Series IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. |
ZHIHAN YUE et. al. |
| 2022 | 4 | An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For example, the retrieved knowledge might be noisy and irrelevant to the question, and the re-embedded knowledge features during reasoning might deviate from their original meanings in the knowledge base (KB). To address this challenge, we propose PICa, a simple yet effective method that Prompts GPT3 via the use of Image Captions, for knowledge-based VQA. |
ZHENGYUAN YANG et. al. |
| 2022 | 5 | FedProto: Federated Prototype Learning Across Heterogeneous Clients IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. |
YUE TAN et. al. |
| 2022 | 6 | TransFG: A Transformer Architecture for Fine-Grained Recognition IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the backbone network to extract features of detected discriminative regions. |
JU HE et. al. |
| 2022 | 7 | Anchor DETR: Query Design for Transformer-Based Detector IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel query design for the transformer-based object detection. |
Yingming Wang; Xiangyu Zhang; Tong Yang; Jian Sun; |
| 2022 | 8 | Vision Transformers Are Robust Learners IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study the robustness of the Vision Transformer (ViT) (Dosovitskiy et al. 2021) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. |
Sayak Paul; Pin-Yu Chen; |
| 2022 | 9 | Low-Light Image Enhancement with Normalizing Flow IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. |
YUFEI WANG et. al. |
| 2022 | 10 | Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The existing methods either have difficulties in balancing the tasks of image enhancement and object detection, or often ignore the latent information beneficial for detection. To alleviate this problem, we propose a novel Image-Adaptive YOLO (IA-YOLO) framework, where each image can be adaptively enhanced for better detection performance. |
WENYU LIU et. al. |
| 2022 | 11 | SSAST: Self-Supervised Audio Spectrogram Transformer IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper focuses on audio and speech classification, and aims to reduce the need for large amounts of labeled data for the AST by leveraging self-supervised learning using unlabeled data. |
Yuan Gong; Cheng-I Lai; Yu-An Chung; James Glass; |
| 2022 | 12 | DiffSinger: Singing Voice Synthesis Via Shallow Diffusion Mechanism IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. |
Jinglin Liu; Chengxi Li; Yi Ren; Feiyang Chen; Zhou Zhao; |
| 2022 | 13 | Graph Neural Controlled Differential Equations for Traffic Forecasting IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present the method of spatio-temporal graph neural controlled differential equation (STG-NCDE). |
Jeongwhan Choi; Hwangyong Choi; Jeehyun Hwang; Noseong Park; |
| 2022 | 14 | Unified Named Entity Recognition As Word-Word Relation Classification IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a novel alternative by modeling the unified NER as word-word relation classification, namely W^2NER. |
JINGYE LI et. al. |
| 2022 | 15 | Augmentation-Free Self-Supervised Learning on Graphs IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel augmentation-free self-supervised learning framework for graphs, named AFGRL. |
Namkyeong Lee; Junseok Lee; Chanyoung Park; |
| 2021 | 1 | Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a ProbSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences’ dependency alignment. |
HAOYI ZHOU et. al. |
| 2021 | 2 | TabNet: Attentive Interpretable Tabular Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. |
Sercan Ö. Arik; Tomas Pfister; |
| 2021 | 3 | R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. |
Xue Yang; Junchi Yan; Ziming Feng; Tao He; |
| 2021 | 4 | Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we take a slightly different viewpoint — we find that precise positioning of raw points is not essential for high performance 3D object detection and that the coarse voxel granularity can also offer sufficient detection accuracy. |
JIAJUN DENG et. al. |
| 2021 | 5 | Graph Neural Network-Based Anomaly Detection in Multivariate Time Series IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Given high-dimensional time series data (e.g., sensor data), how can we detect anomalous events, such as system faults and attacks? |
Ailin Deng; Bryan Hooi; |
| 2021 | 6 | Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To overcome those limitations, our paper proposes a novel Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting. |
Mengzhang Li; Zhanxing Zhu; |
| 2021 | 7 | Contrastive Clustering IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. |
YUNFAN LI et. al. |
| 2021 | 8 | Personalized Cross-Silo Federated Learning on Non-IID Data IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. |
YUTAO HUANG et. al. |
| 2021 | 9 | Beyond Low-frequency Information in Graph Convolutional Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional Networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. |
Deyu Bo; Xiao Wang; Chuan Shi; Huawei Shen; |
| 2021 | 10 | Going Deeper With Directly-Trained Larger Spiking Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed “STBP-tdBN”, enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware. |
Hanle Zheng; Yujie Wu; Lei Deng; Yifan Hu; Guoqi Li; |
| 2021 | 11 | Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Session-based recommendation (SBR) focuses on next-item prediction at a certain time point. As user profiles are generally not available in this scenario, capturing the user … |
XIN XIA et. al. |
| 2021 | 12 | Improving Sample Efficiency in Model-Free Reinforcement Learning from Images IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Following these findings, we propose effective techniques to improve training stability. |
DENIS YARATS et. al. |
| 2021 | 13 | Semi-supervised Medical Image Segmentation Through Dual-task Consistency IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. |
Xiangde Luo; Jieneng Chen; Tao Song; Guotai Wang; |
| 2021 | 14 | Data Augmentation for Graph Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction. |
TONG ZHAO et. al. |
| 2021 | 15 | Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we design a la- bel generation module based on the self-supervised learning strategy to acquire independent unimodal supervisions. |
Wenmeng Yu; Hua Xu; Ziqi Yuan; Jiele Wu; |
| 2020 | 1 | Random Erasing Data Augmentation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). |
Zhun Zhong; Liang Zheng; Guoliang Kang; Shaozi Li; Yi Yang; |
| 2020 | 2 | Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. |
ZHAOHUI ZHENG et. al. |
| 2020 | 3 | PIQA: Reasoning About Physical Commonsense in Natural Language IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. |
Yonatan Bisk; Rowan Zellers; Ronan Le bras; Jianfeng Gao; Yejin Choi; |
| 2020 | 4 | GMAN: A Graph Multi-Attention Network for Traffic Prediction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on the spatio-temporal factors, and propose a graph multi-attention network (GMAN) to predict traffic conditions for time steps ahead at different locations on a road network graph. |
Chuanpan Zheng; Xiaoliang Fan; Cheng Wang; Jianzhong Qi; |
| 2020 | 5 | FFA-Net: Feature Fusion Attention Network for Single Image Dehazing IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. |
Xu Qin; Zhilin Wang; Yuanchao Bai; Xiaodong Xie; Huizhu Jia; |
| 2020 | 6 | Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present TextFooler, a simple but strong baseline to generate adversarial text. |
Di Jin; Zhijing Jin; Joey Tianyi Zhou; Peter Szolovits; |
| 2020 | 7 | Measuring and Relieving The Over-Smoothing Problem for Graph Neural Networks from The Topological View IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a systematic and quantitative study on the over-smoothing issue of GNNs. |
DELI CHEN et. al. |
| 2020 | 8 | Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel model, named Spatial-Temporal Synchronous Graph Convolutional Networks (STSGCN), for spatial-temporal network data forecasting. |
Chao Song; Youfang Lin; Shengnan Guo; Huaiyu Wan; |
| 2020 | 9 | Improved Knowledge Distillation Via Teacher Assistant IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher. |
SEYED IMAN MIRZADEH et. al. |
| 2020 | 10 | EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To resolve this challenge, we propose EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings. |
ALDO PAREJA et. al. |
| 2020 | 11 | Unified Vision-Language Pre-Training for Image Captioning and VQA IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a unified Vision-Language Pre-training (VLP) model. |
LUOWEI ZHOU et. al. |
| 2020 | 12 | Unicoder-VL: A Universal Encoder for Vision and Language By Cross-Modal Pre-Training IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. |
Gen Li; Nan Duan; Yuejian Fang; Ming Gong; Daxin Jiang; |
| 2020 | 13 | ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on this framework, we construct several tasks and train the ERNIE 2.0 model to capture lexical, syntactic and semantic aspects of information in the training data. |
YU SUN et. al. |
| 2020 | 14 | SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on a careful analysis, we propose a set of practical guidelines of target state estimation for high-performance generic object tracker design. |
Yinda Xu; Zeyu Wang; Zuoxin Li; Ye Yuan; Gang Yu; |
| 2020 | 15 | K-BERT: Enabling Language Representation with Knowledge Graph IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For machines to achieve this capability, we propose a knowledge-enabled language representation model (K-BERT) with knowledge graphs (KGs), in which triples are injected into the sentences as domain knowledge. |
WEIJIE LIU et. al. |
| 2019 | 1 | Regularized Evolution For Image Classifier Architecture Search IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. |
Esteban Real; Alok Aggarwal; Yanping Huang; Quoc V. Le; |
| 2019 | 2 | CheXpert: A Large Chest Radiograph Dataset With Uncertainty Labels And Expert Comparison IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients. We release the dataset to the public as a standard benchmark to evaluate performance of chest radiograph interpretation models. |
JEREMY IRVIN et. al. |
| 2019 | 3 | Attention Based Spatial-Temporal Graph Convolutional Networks For Traffic Flow Forecasting IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel attention based spatial-temporal graph convolutional network (ASTGCN) model to solve traffic flow forecasting problem. |
Shengnan Guo; Youfang Lin; Ning Feng; Chao Song; Huaiyu Wan; |
| 2019 | 4 | Graph Convolutional Networks For Text Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose to use graph convolutional networks for text classification. |
Liang Yao; Chengsheng Mao; Yuan Luo; |
| 2019 | 5 | Weisfeiler And Leman Go Neural: Higher-Order Graph Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on this, we propose a generalization of GNNs, so-called k-dimensional GNNs (k-GNNs), which can take higher-order graph structures at multiple scales into account. |
CHRISTOPHER MORRIS et. al. |
| 2019 | 6 | Session-Based Recommendation With Graph Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To obtain accurate item embedding and take complex transitions of items into account, we propose a novel method, i.e. Session-based Recommendation with Graph Neural Networks, SR-GNN for brevity. |
SHU WU et. al. |
| 2019 | 7 | Hypergraph Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph structure. |
Yifan Feng; Haoxuan You; Zizhao Zhang; Rongrong Ji; Yue Gao; |
| 2019 | 8 | Deep Interest Evolution Network For Click-Through Rate Prediction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel model, named Deep Interest Evolution Network (DIEN), for CTR prediction. |
GUORUI ZHOU et. al. |
| 2019 | 9 | Interpretation Of Neural Networks Is Fragile IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we demonstrate how to generate adversarial perturbations that produce perceptively indistinguishable inputs that are assigned the same predicted label, yet have very different interpretations. |
Amirata Ghorbani; Abubakar Abid; James Zou; |
| 2019 | 10 | M2Det: A Single-Shot Object Detector Based On Multi-Level Feature Pyramid Network IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Newly, in this work, we present Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. |
QIJIE ZHAO et. al. |
| 2019 | 11 | Neural Speech Synthesis With Transformer Network IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the success of Transformer network in neural machine translation (NMT), in this paper, we introduce and adapt the multi-head attention mechanism to replace the RNN structures and also the original attention mechanism in Tacotron2. |
Naihan Li; Shujie Liu; Yanqing Liu; Sheng Zhao; Ming Liu; |
| 2019 | 12 | ATOMIC: An Atlas Of Machine Commonsense For If-Then Reasoning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. |
MAARTEN SAP et. al. |
| 2019 | 13 | Spatiotemporal Multi-Graph Convolution Network For Ride-Hailing Demand Forecasting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the spatiotemporal multi-graph convolution network (ST-MGCN), a novel deep learning model for ride-hailing demand forecasting. |
XU GENG et. al. |
| 2019 | 14 | Revisiting Spatial-Temporal Similarity: A Deep Learning Framework For Traffic Prediction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. |
Huaxiu Yao; Xianfeng Tang; Hua Wei; Guanjie Zheng; Zhenhui Li; |
| 2019 | 15 | DialogueRNN: An Attentive RNN For Emotion Detection In Conversations IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe a new method based on recurrent neural networks that keeps track of the individual party states throughout the conversation and uses this information for emotion classification. |
NAVONIL MAJUMDER et. al. |
| 2018 | 1 | Spatial Temporal Graph Convolutional Networks For Skeleton-Based Action Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. |
Sijie Yan; Yuanjun Xiong; Dahua Lin; |
| 2018 | 2 | Deeper Insights Into Graph Convolutional Networks For Semi-Supervised Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop deeper insights into the GCN model and address its fundamental limits. |
Qimai Li; Zhichao Han; Xiao-ming Wu; |
| 2018 | 3 | Convolutional 2D Knowledge Graph Embeddings IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. |
Tim Dettmers; Pasquale Minervini; Pontus Stenetorp; Sebastian Riedel; |
| 2018 | 4 | Rainbow: Combining Improvements In Deep Reinforcement Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper examines six extensions to the DQN algorithm and empirically studies their combination. |
MATTEO HESSEL et. al. |
| 2018 | 5 | FiLM: Visual Reasoning With A General Conditioning Layer IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. |
Ethan Perez; Florian Strub; Harm de Vries; Vincent Dumoulin; Aaron Courville; |
| 2018 | 6 | Counterfactual Multi-Agent Policy Gradients IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. |
Jakob N. Foerster; Gregory Farquhar; Triantafyllos Afouras; Nantas Nardelli; Shimon Whiteson; |
| 2018 | 7 | Anchors: High-Precision Model-Agnostic Explanations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an algorithm to efficiently compute these explanations for any black-box model with high-probability guarantees. |
Marco Tulio Ribeiro; Sameer Singh; Carlos Guestrin; |
| 2018 | 8 | Deep Reinforcement Learning That Matters IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate challenges posed by reproducibility, proper experimental techniques, and reporting procedures. |
PETER HENDERSON et. al. |
| 2018 | 9 | An End-to-End Deep Learning Architecture For Graph Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. |
Muhan Zhang; Zhicheng Cui; Marion Neumann; Yixin Chen; |
| 2018 | 10 | Learning To Generalize: Meta-Learning For Domain Generalization IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel meta-learning method for domain generalization. |
Da Li; Yongxin Yang; Yi-Zhe Song; Timothy M. Hospedales; |
| 2018 | 11 | Deep Multi-View Spatial-Temporal Network For Taxi Demand Prediction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. |
HUAXIU YAO et. al. |
| 2018 | 12 | Deep Q-learning From Demonstrations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we study a setting where the agent may access data from previous control of the system. |
TODD HESTER et. al. |
| 2018 | 13 | Spatial As Deep: Spatial CNN For Traffic Scene Understanding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Spatial CNN (SCNN), which generalizes traditional deep layer-by-layer convolutions to slice-by-slice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer. |
Xingang Pan; Jianping Shi; Ping Luo; Xiaogang Wang; Xiaoou Tang; |
| 2018 | 14 | Wasserstein Distance Guided Representation Learning For Domain Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WDGRL). |
Jian Shen; Yanru Qu; Weinan Zhang; Yong Yu; |
| 2018 | 15 | Multi-Adversarial Domain Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a multi-adversarial domain adaptation (MADA) approach, which captures multimode structures to enable fine-grained alignment of different data distributions based on multiple domain discriminators. |
Zhongyi Pei; Zhangjie Cao; Mingsheng Long; Jianmin Wang; |
| 2017 | 1 | Inception-v4, Inception-ResNet And The Impact Of Residual Connections On Learning IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we give clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly. |
Christian Szegedy; Sergey Ioffe; Vincent Vanhoucke; Alexander A Alemi; |
| 2017 | 2 | ConceptNet 5.5: An Open Multilingual Graph Of General Knowledge IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be used with modern NLP techniques such as word embeddings. |
Robert Speer; Joshua Chin; Catherine Havasi; |
| 2017 | 3 | SeqGAN: Sequence Generative Adversarial Nets With Policy Gradient IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a sequence generation framework, called SeqGAN, to solve the problems. |
Lantao Yu; Weinan Zhang; Jun Wang; Yong Yu; |
| 2017 | 4 | Deep Spatio-Temporal Residual Networks For Citywide Crowd Flows Prediction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast the inflow and outflow of crowds in each and every region of a city. |
Junbo Zhang; Yu Zheng; Dekang Qi; |
| 2017 | 5 | SummaRuNNer: A Recurrent Neural Network Based Sequence Model For Extractive Summarization Of Documents IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. |
Ramesh Nallapati; Feifei Zhai; Bowen Zhou; |
| 2017 | 6 | A Hierarchical Latent Variable Encoder-Decoder Model For Generating Dialogues IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To model these dependencies in a generative framework, we propose a neural network-based generative architecture, with stochastic latent variables that span a variable number of time steps. |
IULIAN VLAD SERBAN et. al. |
| 2017 | 7 | The Option-Critic Architecture IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We derive policy gradient theorems for options and propose a new option-critic architecture capable of learning both the internal policies and the termination conditions of options, in tandem with the policy over options, and without the need to provide any additional rewards or subgoals. |
Pierre-Luc Bacon; Jean Harb; Doina Precup; |
| 2017 | 8 | An End-to-End Spatio-Temporal Attention Model For Human Action Recognition From Skeleton Data IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an end-to-end spatial and temporal attention model for human action recognition from skeleton data. |
Sijie Song; Cuiling Lan; Junliang Xing; Wenjun Zeng; Jiaying Liu; |
| 2017 | 9 | Robust Loss Functions Under Label Noise For Deep Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we provide some sufficient conditions on a loss function so that risk minimization under that loss function would be inherently tolerant to label noise for multiclass classification problems. |
Aritra Ghosh; Himanshu Kumar; P. S. Sastry; |
| 2017 | 10 | TextBoxes: A Fast Text Detector With A Single Deep Neural Network IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. |
Minghui Liao; Baoguang Shi; Xiang Bai; Xinggang Wang; Wenyu Liu; |
| 2017 | 11 | Community Preserving Network Embedding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel Modularized Nonnegative Matrix Factorization (M-NMF) model to incorporate the community structure into network embedding. |
XIAO WANG et. al. |
| 2017 | 12 | Playing FPS Games With Deep Reinforcement Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method to augment these models to exploit game feature information such as the presence of enemies or items, during the training phase. |
Guillaume Lample; Devendra Singh Chaplot; |
| 2017 | 13 | Online Multi-Target Tracking Using Recurrent Neural Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). |
Anton Milan; S. Hamid Rezatofighi; Anthony Dick; Ian Reid; Konrad Schindler; |
| 2017 | 14 | Topic Aware Neural Response Generation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. |
CHEN XING et. al. |
| 2017 | 15 | DeepFix: Fixing Common C Language Errors By Deep Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present an end-to-end solution, called DeepFix, that can fix multiple such errors in a program without relying on any external tool to locate or fix them. |
Rahul Gupta; Soham Pal; Aditya Kanade; Shirish Shevade; |
| 2016 | 1 | Deep Reinforcement Learning With Double Q-Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we answer all these questions affirmatively. |
Hado van Hasselt; Arthur Guez; David Silver; |
| 2016 | 2 | Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. |
Iulian V. Serban; Alessandro Sordoni; Yoshua Bengio; Aaron Courville; Joelle Pineau; |
| 2016 | 3 | Character-Aware Neural Language Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a simple neural language model that relies only on character-level inputs. |
Yoon Kim; Yacine Jernite; David Sontag; Alexander M. Rush; |
| 2016 | 4 | Return Of Frustratingly Easy Domain Adaptation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). |
Baochen Sun; Jiashi Feng; Kate Saenko; |
| 2016 | 5 | Holographic Embeddings Of Knowledge Graphs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. |
Maximilian Nickel; Lorenzo Rosasco; Tomaso Poggio; |
| 2016 | 6 | Deep Neural Networks For Learning Graph Representations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information. |
Shaosheng Cao; Wei Lu; Qiongkai Xu; |
| 2016 | 7 | Siamese Recurrent Architectures For Learning Sentence Similarity IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a siamese adaptation of the Long Short-Term Memory (LSTM) network for labeled data comprised of pairs of variable-length sequences. |
Jonas Mueller; Aditya Thyagarajan; |
| 2016 | 8 | Co-Occurrence Feature Learning For Skeleton Based Action Recognition Using Regularized Deep LSTM Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To train the deep LSTM network effectively, we propose a new dropout algorithm which simultaneously operates on the gates, cells, and output responses of the LSTM neurons. |
WENTAO ZHU et. al. |
| 2016 | 9 | Predicting The Next Location: A Recurrent Model With Spatial And Temporal Contexts IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we extend RNN and propose a novel method called Spatial Temporal Recurrent Neural Networks (ST-RNN). |
Qiang Liu; Shu Wu; Liang Wang; Tieniu Tan; |
| 2016 | 10 | VBPR: Visual Bayesian Personalized Ranking From Implicit Feedback IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a scalable factorization model to incorporate visual signals into predictors of people’s opinions, which we apply to a selection of large, real-world datasets. |
Ruining He; Julian McAuley; |
| 2016 | 11 | Convolutional Neural Networks Over Tree Structures For Programming Language Processing IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel tree-based convolutional neural network (TBCNN) for programming language processing, in which a convolution kernel is designed over programs’ abstract syntax trees to capture structural information. |
Lili Mou; Ge Li; Lu Zhang; Tao Wang; Zhi Jin; |
| 2016 | 12 | The Constrained Laplacian Rank Algorithm For Graph-Based Clustering IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We derive optimization algorithms to solve these objectives. |
Feiping Nie; Xiaoqian Wang; Michael I. Jordan; Heng Huang; |
| 2016 | 13 | Representation Learning Of Knowledge Graphs With Entity Descriptions IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel RL method for knowledge graphs taking advantages of entity descriptions. |
Ruobing Xie; Zhiyuan Liu; Jia Jia; Huanbo Luan; Maosong Sun; |
| 2016 | 14 | Deep Hashing Network For Efficient Similarity Retrieval IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel Deep Hashing Network (DHN) architecture for supervised hashing, in which we jointly learn good image representation tailored to hash coding and formally control the quantization error. |
Han Zhu; Mingsheng Long; Jianmin Wang; Yue Cao; |
| 2016 | 15 | Text Matching As Image Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. |
LIANG PANG et. al. |
| 2015 | 1 | Learning Entity And Relation Embeddings For Knowledge Graph Completion IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider the approach of knowledge graph embeddings. |
Yankai Lin; Zhiyuan Liu; Maosong Sun; Yang Liu; Xuan Zhu; |
| 2015 | 2 | Recurrent Convolutional Neural Networks For Text Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In contrast to traditional methods, we introduce a recurrent convolutional neural network for text classification without human-designed features. |
Siwei Lai; Liheng Xu; Kang Liu; Jun Zhao; |
| 2015 | 3 | The Network Data Repository With Interactive Graph Analytics And Visualization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: NetworkRepository (NR) is the first interactive data repository with a web-based platform for visual interactive analytics. Unlike other data repositories (e.g., UCI ML Data … |
Ryan Rossi; Nesreen Ahmed; |
| 2015 | 4 | Obtaining Well Calibrated Probabilities Using Bayesian Binning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a new non-parametric calibration method called Bayesian Binning into Quantiles (BBQ) which addresses key limitations of existing calibration methods. |
Mahdi Pakdaman Naeini; Gregory Cooper; Milos Hauskrecht; |
| 2015 | 5 | Never-Ending Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a never-ending learning paradigm for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. |
TOM M. MITCHELL et. al. |
| 2015 | 6 | TrustSVD: Collaborative Filtering With Both The Explicit And Implicit Influence Of User Trust And Of Item Ratings IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To help resolve these issues, we propose TrustSVD, a trust-based matrix factorization technique. |
Guibing Guo; Jie Zhang; Neil Yorke-Smith; |
| 2015 | 7 | Robust Image Sentiment Analysis Using Progressively Trained And Domain Transferred Deep Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by the needs in leveraging large scale yet noisy training data to solve the extremely challenging problem of image sentiment analysis, we employ Convolutional Neural Networks (CNN). |
Quanzeng You; Jiebo Luo; Hailin Jin; Jianchao Yang; |
| 2015 | 8 | Self-Paced Curriculum Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we discover the missing link between CL and SPL, and propose a unified framework named self-paced curriculum leaning (SPCL). |
Lu Jiang; Deyu Meng; Qian Zhao; Shiguang Shan; Alexander G. Hauptmann; |
| 2015 | 9 | Large-Scale Multi-View Spectral Clustering Via Bipartite Graph IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the problem of large-scale multi-view spectral clustering. |
Yeqing Li; Feiping Nie; Heng Huang; Junzhou Huang; |
| 2015 | 10 | Initializing Bayesian Hyperparameter Optimization Via Meta-Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we mimic a strategy human domain experts use: speed up optimization by starting from promising configurations that performed well on similar datasets. |
Matthias Feurer; Jost Tobias Springenberg; Frank Hutter; |
| 2015 | 11 | Topical Word Embeddings IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both words and their topics. |
Yang Liu; Zhiyuan Liu; Tat-Seng Chua; Maosong Sun; |
| 2015 | 12 | Using Machine Teaching To Identify Optimal Training-Set Attacks On Machine Learners IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate a problem at the intersection of machine learning and security: training-set attacks on machine learners. |
Shike Mei; Xiaojin Zhu; |
| 2015 | 13 | Lazier Than Lazy Greedy IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop the first linear-time algorithm for maximizing a general monotone submodular function subject to a cardinality constraint. |
Baharan Mirzasoleiman; Ashwinkumar Badanidiyuru; Amin Karbasi; Jan Vondrak; Andreas Krause; |
| 2015 | 14 | Surpassing Human-Level Face Verification Performance On LFW With GaussianFace IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To enhance discriminative power, we introduced a more efficient equivalent form of Kernel Fisher Discriminant Analysis to DGPLVM.To speed up the process of inference and prediction, we exploited the low rank approximation method. |
Chaochao Lu; Xiaoou Tang; |
| 2015 | 15 | Jointly Modeling Deep Video And Compositional Text To Bridge Vision And Language In A Unified Framework IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a unified framework that jointly models video and the corresponding text sentences. |
Ran Xu; Caiming Xiong; Wei Chen; Jason J Corso; |
| 2014 | 1 | Knowledge Graph Embedding By Translating On Hyperplanes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To make a good trade-off between model capacity and efficiency, in this paper we propose TransH which models a relation as a hyperplane together with a translation operation on it. |
Zhen Wang; Jianwen Zhang; Jianlin Feng; Zheng Chen; |
| 2014 | 2 | Supervised Hashing For Image Retrieval Via Image Representation Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a supervised hashing method for image retrieval, in which we automatically learn a good image representation tailored to hashing as well as a set of hash functions. |
Rongkai Xia; Yan Pan; Hanjiang Lai; Cong Liu; Shuicheng Yan; |
| 2014 | 3 | Robust Multi-View Spectral Clustering Via Low-Rank And Sparse Decomposition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In thispaper, we propose a novel Markov chain method for RobustMulti-view Spectral Clustering (RMSC). |
Rongkai Xia; Yan Pan; Lei Du; Jian Yin; |
| 2014 | 4 | Learning Deep Representations For Graph Clustering IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we explore the possibility of employing deep learning in graph clustering. |
Fei Tian; Bin Gao; Qing Cui; Enhong Chen; Tie-Yan Liu; |
| 2014 | 5 | Large-Scale Supervised Multimodal Hashing With Semantic Correlation Maximization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a novel SMH method, called semantic correlation maximization~(SCM), is proposed to seamlessly integrate semantic labels into the hashing learning procedure for large-scale data modeling. |
Dongqing Zhang; Wu-Jun Li; |
| 2014 | 6 | SenticNet 3: A Common And Common-Sense Knowledge Base For Cognition-Driven Sentiment Analysis IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Rather than using graph-mining and dimensionality-reduction techniques, SenticNet 3 makes use of energy flows to connect various parts of extended common and common-sense knowledge representations to one another. |
Erik Cambria; Daniel Olsher; Dheeraj Rajagopal; |
| 2014 | 7 | Partial Multi-View Clustering IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper,we present possibly the first study on partial multiviewclustering. |
Shao-Yuan Li; Yuan Jiang; Zhi-Hua Zhou; |
| 2014 | 8 | Sequential Click Prediction For Sponsored Search With Recurrent Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by these observations, we introduce a novel framework based on Recurrent Neural Networks (RNN). |
YUYU ZHANG et. al. |
| 2014 | 9 | TopicMF: Simultaneously Exploiting Ratings And Reviews For Recommendation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel matrix factorization model (called TopicMF) which simultaneously considers the ratings and accompanied review texts. |
Yang Bao; Hui Fang; Jie Zhang; |
| 2014 | 10 | Modeling And Predicting Popularity Dynamics Via Reinforced Poisson Processes IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we propose a generative probabilistic framework using a reinforced Poisson process to explicitly model the process through which individual items gain their popularity. |
Huawei Shen; Dashun Wang; Chaoming Song; Albert-László Barabási; |
| 2014 | 11 | Automatic Construction And Natural-Language Description Of Nonparametric Regression Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the beginnings of an automatic statistician, focusing on regression problems. |
James Robert Lloyd; David Duvenaud; Roger Grosse; Joshua Tenenbaum; Zoubin Ghahramani; |
| 2014 | 12 | A Convex Formulation For Semi-Supervised Multi-Label Feature Selection IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel convex semi-supervised multi-label feature selection algorithm, which can be applied to large-scale datasets. |
Xiaojun Chang; Feiping Nie; Yi Yang; Heng Huang; |
| 2014 | 13 | Robust Visual Robot Localization Across Seasons Using Network Flows IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel approach to visual localization of mobile robots in outdoor environments, which is able to deal with substantial seasonal changes. |
Tayyab Naseer; Luciano Spinello; Wolfram Burgard; Cyrill Stachniss; |
| 2014 | 14 | Mapping Users Across Networks By Manifold Alignment On Hypergraph IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to utilize social structures to improve the mapping performance. |
SHULONG TAN et. al. |
| 2014 | 15 | Hybrid Heterogeneous Transfer Learning Through Deep Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a new transfer learning framework called Hybrid Heterogeneous Transfer Learning (HHTL), which allows the corresponding instances across domains to be biased in either the source or target domain. |
Joey Tianyi Zhou; Sinno Jialin Pan; Ivor W. Tsang; Yan Yan; |
| 2013 | 1 | Locate The Hate: Detecting Tweets Against Blacks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The classifier has a 76% average accuracy on individual tweets, suggesting that with further improvements, our work can contribute data on the sources of anti-black hate speech. |
Irene Kwok; Yuzhou Wang; |
| 2013 | 2 | Structure And Intractability Of Optimal Multi-Robot Path Planning On Graphs IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the structure and computational complexity of optimal multi-robot path planning problems on graphs. |
Jingjin Yu; Steven M. LaValle; |
| 2013 | 3 | Generating Natural-Language Video Descriptions Using Text-Mined Knowledge IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a holistic data-driven technique that generates natural-language descriptions for videos. |
Niveda Krishnamoorthy; Girish Malkarnenkar; Raymond Mooney; Kate Saenko; Sergio Guadarrama; |
| 2013 | 4 | Story Generation With Crowdsourced Plot Graphs IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel class of story generation system that can generate stories in an unknown domain. |
Boyang Li; Stephen Lee-Urban; George Johnston; Mark Riedl; |
| 2013 | 5 | Analyzing The Effectiveness Of Adversary Modeling In Security Games IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent deployments of Stackelberg security games (SSG) have led to two competing approaches to handle boundedly rational human adversaries: (1) integrating models of human (adversary) decision-making into the game-theoretic algorithms, and (2) applying robust optimization techniques that avoid adversary modeling. |
Thanh Hong Nguyen; Rong Yang; Amos Azaria; Sarit Kraus; Milind Tambe; |
| 2013 | 6 | Supervised Coupled Dictionary Learning With Group Structures For Multi-modal Retrieval IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce coupled dictionary learning (DL) into supervised sparse coding for multi-modal (cross-media) retrieval. |
Yue Ting Zhuang; Yan Fei Wang; Fei Wu; Yin Zhang; Wei Ming Lu; |
| 2013 | 7 | A General Formal Framework For Pathfinding Problems With Multiple Agents IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by such applications, we introduce a formal framework that is general enough to address all these problems: we use the expressive high-level representation formalism and efficient solvers of the declarative programming paradigm Answer Set Programming. |
Esra Erdem; Doga Gizem Kisa; Umut Oztok; Peter Schüller; |
| 2013 | 8 | Learning Collaborative Impedance-Based Robot Behaviors IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a framework to transfer impedance-based behaviors to a torque-controlled robot by kinesthetic teaching. |
Leonel Dario Rozo; Sylvain Calinon; Darwin Caldwell; Pablo Jimenez; Carme Torras; |
| 2013 | 9 | Convex Subspace Representation Learning From Multi-View Data IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel convex subspace representation learning method for unsupervised multi-view clustering. |
Yuhong Guo; |
| 2013 | 10 | A Hierarchical Aspect-Sentiment Model For Online Reviews IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a hierarchical aspect sentiment model (HASM) to discover a hierarchical structure of aspect-based sentiments from unlabeled online reviews. |
Suin Kim; Jianwen Zhang; Zheng Chen; Alice Oh; Shixia Liu; |
| 2013 | 11 | Multi-Armed Bandit With Budget Constraint And Variable Costs IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose two UCB based algorithms for the new setting. |
Wenkui Ding; Tao Qin; Xu-Dong Zhang; Tie-Yan Liu; |
| 2013 | 12 | Better Human Computation Through Principled Voting IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our short-term goal is to motivate the design of better human computation systems; our long-term goal is to spark an interaction between researchers in (computational) social choice and human computation. |
Andrew Mao; Ariel D. Procaccia; Yiling Chen; |
| 2013 | 13 | Spectral Rotation Versus K-Means In Spectral Clustering IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to impose an additional orthonormal constraint to better approximate the optimal continuous solution to the graph cut objective functions. |
Jin Huang; Feiping Nie; Heng Huang; |
| 2013 | 14 | Data-Efficient Generalization Of Robot Skills With Contextual Policy Search IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new model-based policy search approach that can also learn contextual upper-level policies. |
Andras Gabor Kupcsik; Marc Peter Deisenroth; Jan Peters; Gerhard Neumann; |
| 2013 | 15 | A Robust Bayesian Truth Serum For Non-Binary Signals IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Several mechanisms have been proposed for incentivizing truthful reports of a private signals owned by rational agents, among them the peer prediction method and the Bayesian … |
Goran Radanovic; Boi Faltings; |
| 2012 | 1 | Fused Matrix Factorization With Geographical And Social Influence In Location-Based Social Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, to the best of our knowledge, we are the first to fuse MF with geographical and social influence for POI recommendation in LBSNs. |
Chen Cheng; Haiqin Yang; Irwin King; Michael R. Lyu; |
| 2012 | 2 | Fine-Grained Entity Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper defines a fine-grained set of 112 tags, formulates the tagging problem as multi-class, multi-label classification, describes an unsupervised method for collecting training data, and presents the FIGER implementation. |
Xiao Ling; Daniel S. Weld; |
| 2012 | 3 | Unsupervised Feature Selection Using Nonnegative Spectral Analysis IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a new unsupervised learning algorithm, namely Nonnegative Discriminative Feature Selection (NDFS), is proposed. |
Zechao Li; Yi Yang; Jing Liu; Xiaofang Zhou; Hanqing Lu; |
| 2012 | 4 | Non-Intrusive Load Monitoring Using Prior Models Of General Appliance Types IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose an approach by which individual appliances can be iteratively separated from an aggregate load. |
Oliver Parson; Siddhartha Ghosh; Mark Weal; Alex Rogers; |
| 2012 | 5 | Online Task Assignment In Crowdsourcing Markets IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by recent research on the online adwords problem, we present a two-phase exploration-exploitation assignment algorithm and prove that it is competitive with respect to the optimal offline algorithm which has access to the unknown skill levels of each worker. |
Chien-Ju Ho; Jennifer Wortman Vaughan; |
| 2012 | 6 | Low-Rank Matrix Recovery Via Efficient Schatten P-Norm Minimization IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel Schatten $p$-Norm optimization framework that unifies different norm formulations. |
Feiping Nie; Heng Huang; Chris Ding; |
| 2012 | 7 | Emoticon Smoothed Language Models For Twitter Sentiment Analysis IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel model, called emoticon smoothed language model (ESLAM), to handle this challenge. |
Kun-Lin Liu; Wu-Jun Li; Minyi Guo; |
| 2012 | 8 | Multi-Label Learning By Exploiting Label Correlations Locally IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the ML-LOC approach which allows label correlations to be exploited locally. |
Sheng-Jun Huang; Zhi-Hua Zhou; |
| 2012 | 9 | Automatic Targetless Extrinsic Calibration Of A 3D Lidar And Camera By Maximizing Mutual Information IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper reports on a mutual information (MI) based algorithm for automatic extrinsic calibration of a 3D laser scanner and optical camera system. |
Gaurav Pandey; James R. McBride; Silvio Savarese; Ryan M. Eustice; |
| 2012 | 10 | Transfer Learning With Graph Co-Regularization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel approach called Graph co-regularized Transfer Learning (GTL) for this purpose, which integrates the two objective functions seamlessly into one unified optimization problem. |
Mingsheng Long; Jianmin Wang; Guiguang Ding; Dou Shen; Qiang Yang; |
| 2012 | 11 | TRUSTS: Scheduling Randomized Patrols For Fare Inspection In Transit Systems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present TRUSTS, an application for scheduling randomized patrols for fare inspection in transit systems. |
ZHENGYU YIN et. al. |
| 2012 | 12 | Query Rewriting For Horn-SHIQ Plus Rules IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a rewriting-based algorithm for conjunctive query answering over Horn-SHIQ ontologies, possibly extended with recursive rules under limited recursion as in DL+log. |
Thomas Eiter; Magdalena Ortiz; Mantas Simkus; Trung-Kien Tran; Guohui Xiao; |
| 2012 | 13 | A Robust Bayesian Truth Serum For Small Populations IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a robust BTS for the elicitation of binary information which is incentive compatible for everyn >= 3, taking advantage of a particularity of the quadratic scoring rule. |
Jens Witkowski; David C. Parkes; |
| 2012 | 14 | Predicting Disease Transmission From Geo-Tagged Micro-Blog Data IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We construct a probabilistic model that can predict if and when an individual will fall ill with high precision and good recall on the basis of his social ties and co-locations with other people, as revealed by their Twitter posts. |
Adam Sadilek; Henry Kautz; Vincent Silenzio; |
| 2012 | 15 | Document Summarization Based On Data Reconstruction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we take a different perspective from data reconstruction and propose a novel framework named Document Summarization based on Data Reconstruction (DSDR). |
ZHANYING HE et. al. |
| 2011 | 1 | Learning Structured Embeddings Of Knowledge Bases IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a learning process based on an innovative neural network architecture designed to embed any of these symbolic representations into a more flexible continuous vector space in which the original knowledge is kept and enhanced. |
Antoine Bordes; Jason Weston; Ronan Collobert; Yoshua Bengio; |
| 2011 | 2 | Understanding Natural Language Commands For Robotic Navigation And Mobile Manipulation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a new model for understanding natural language commands given to autonomous systems that perform navigation and mobile manipulation in semi-structured environments. |
STEFANIE TELLEX et. al. |
| 2011 | 3 | Learning To Interpret Natural Language Navigation Instructions From Observations IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a system that learns to transform natural-language navigation instructions into executable formal plans. |
David L. Chen; Raymond J. Mooney; |
| 2011 | 4 | Large Scale Spectral Clustering With Landmark-Based Representation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel approach, called Landmark-based Spectral Clustering (LSC), for large scale clustering problems. |
Xinlei Chen; Deng Cai; |
| 2011 | 5 | Heterogeneous Transfer Learning For Image Classification IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We empirically demonstrate the effectiveness of our algorithm on the Caltech-256 image dataset. |
YIN ZHU et. al. |
| 2011 | 6 | Online Graph Pruning For Pathfinding On Grid Maps IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a novel search strategy, specific to grids, which is fast, optimal and requires no memory overhead. |
Daniel Damir Harabor; Alban Grastien; |
| 2011 | 7 | Value Function Approximation In Reinforcement Learning Using The Fourier Basis IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the Fourier basis, a linear value function approximation scheme based on the Fourier series. |
George Konidaris; Sarah Osentoski; Philip Thomas; |
| 2011 | 8 | Transportability Of Causal And Statistical Relations: A Formal Approach IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a formal representation called "selection diagrams" for expressing knowledge about differences and commonalities between environments and, using this representation, we derive procedures for deciding whether effects in the target environment can be inferred from experiments conducted elsewhere. |
Judea Pearl; Elias Bareinboim; |
| 2011 | 9 | Simulated Annealing Based Influence Maximization In Social Networks IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a totally different approach based on Simulated Annealing(SA) for the influence maximization problem. |
QINGYE JIANG et. al. |
| 2011 | 10 | Efficient Energy-Optimal Routing For Electric Vehicles IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper shows how these challenges can be met within the framework of A* search. |
Martin Sachenbacher; Martin Leucker; Andreas Artmeier; Julian Haselmayr; |
| 2011 | 11 | Controlling Selection Bias In Causal Inference IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper highlights several graphical and algebraic methods capable of mitigating and sometimes eliminating this bias. |
Elias Bareinboim; Judea Pearl; |
| 2011 | 12 | Can Collective Sentiment Expressed On Twitter Predict Political Elections? IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper applies methods used in studies that have shown a direct correlation between volume/sentiment of Twitter chatter and future electoral results in a new dataset about political elections. |
Jessica Elan Chung; Eni Mustafaraj; |
| 2011 | 13 | Convergence Properties Of (μ + Λ) Evolutionary Algorithms IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a number of convergence properties of population-based Evolutionary Algorithms (EAs) on a set of test functions. |
Aram Ter-Sarkisov; Stephen Marsland; |
| 2011 | 14 | Optimal Route Planning For Electric Vehicles In Large Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the problem of routing electric vehicles (EV) in the most energy-efficient way within a road network taking into account both their limited energy supply as well as their ability to recuperate energy. |
Jochen Eisner; Stefan Funke; Sabine Storandt; |
| 2011 | 15 | Semantic Relatedness Using Salient Semantic Analysis IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a novel method for measuring semantic relatedness using semantic profiles constructed from salient encyclopedic features. |
Samer Hassan Hassan; Rada Mihalcea; |
| 2010 | 1 | Toward An Architecture For Never-Ending Language Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, we propose an approach and a set of design principles for such an agent, describe a partial implementation of such a system that has already learned to extract a knowledge base containing over 242,000 beliefs with an estimated precision of 74% after running for 67 days, and discuss lessons learned from this preliminary attempt to build a never-ending learning agent. |
ANDREW CARLSON et. al. |
| 2010 | 2 | Relative Entropy Policy Search IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. |
Jan Peters; Katharina Mulling; Yasemin Altun; |
| 2010 | 3 | Facial Age Estimation By Learning From Label Distributions IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an algorithm named IIS-LLD for learning from the label distributions, which is an iterative optimization process based on the maximum entropy model. |
Xin Geng; Kate Smith-Miles; Zhi-Hua Zhou; |
| 2010 | 4 | Ad Hoc Autonomous Agent Teams: Collaboration Without Pre-Coordination IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper challenges the AI community to develop theory and to implement prototypes of ad hoc team agents. |
Peter Stone; Gal A. Kaminka; Sarit Kraus; Jeffrey S. Rosenschein; |
| 2010 | 5 | Collaborative Filtering Meets Mobile Recommendation: A User-Centered Approach IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a new approach, known as user-centered collaborative location and activity filtering (UCLAF), to pull many users’ data together and apply collaborative filtering to find like-minded users and like-patterned activities at different locations. |
Vincent W. Zheng; Bin Cao; Yu Zheng; Xing Xie; Qiang Yang; |
| 2010 | 6 | Transfer Learning In Collaborative Filtering For Sparsity Reduction IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the data sparsity problem in a target domain by transferring knowledge about both users and items from auxiliary data sources. |
Weike Pan; Evan Wei Xiang; Nathan Nan Liu; Qiang Yang; |
| 2010 | 7 | Finding Optimal Solutions To Cooperative Pathfinding Problems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the first practical, admissible, and complete algorithm for solving problems of this kind. |
Trevor Scott Standley; |
| 2010 | 8 | Probabilistic Plan Recognition Using Off-the-Shelf Classical Planners IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we extend this approach to the more general problem of probabilistic plan recognition where a probability distribution over the set of goals is sought under the assumptions that actions have deterministic effects and both agent and observer have complete information about the initial state. |
Miguel Ram�rez; Hector Geffner; |
| 2010 | 9 | Efficient Spectral Feature Selection With Minimum Redundancy IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a novel spectral feature selection algorithm to handle feature redundancy, adopting an embedded model. |
Zheng Zhao; Lei Wang; Huan Liu; |
| 2010 | 10 | Sentiment Analysis With Global Topics And Local Dependency IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a major departure from the previous approaches by making two linked contributions. |
Fangtao Li; Minlie Huang; Xiaoyan Zhu; |
| 2010 | 11 | Hydra: Automatically Configuring Algorithms For Portfolio-Based Selection IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we introduce Hydra, a novel technique for combining these two methods, thereby realizing the benefits of both. |
Lin Xu; Holger Hoos; Kevin Leyton-Brown; |
| 2010 | 13 | Multi-Label Learning With Weak Label IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the WELL (WEak Label Learning) method to solve the weak label problem. |
Yu-Yin Sun; Yin Zhang; Zhi-Hua Zhou; |
| 2010 | 14 | Complexity Of Computing Optimal Stackelberg Strategies In Security Resource Allocation Games IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study how to compute optimal Stackelberg strategies in such games, showing that this can be done in polynomial time in some cases, and is NP-hard in others. |
Dmytro Korzhyk; Vincent Conitzer; Ronald Parr; |
| 2010 | 15 | Truth, Justice, And Cake Cutting IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we investigate the problem of cutting a cake in a way that is truthful and fair, where for the first time our notion of dominant strategy truthfulness is the ubiquitous one in social choice and computer science. |
Yiling Chen; John Lai; David Parkes; Ariel D. Procaccia; |
| 2008 | 1 | Maximum Entropy Inverse Reinforcement Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop a probabilistic approach based on the principle of maximum entropy. |
Brian D. Ziebart; Andrew Maas; J. Andrew Bagnell; Anind K. Dey; |
| 2008 | 2 | Transfer Learning Via Dimensionality Reduction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider transfer learning via dimensionality reduction. |
Sinno Jialin Pan; James T. Kwok; Qiang Yang; |
| 2008 | 3 | Zero-data Learning Of New Tasks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or tasks are provided. |
Hugo Larochelle; Dumitru Erhan; Yoshua Bengio; |
| 2008 | 4 | Single Document Keyphrase Extraction Using Neighborhood Knowledge IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing methods for single document keyphrase extraction usually make use of only the information contained in the specified document. |
Xiaojun Wan; Jianguo Xiao; |
| 2008 | 5 | Trace Ratio Criterion For Feature Selection IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we directly optimize the subset-level score, and propose a novel algorithm to efficiently find the global optimal feature subset such that the subset-level score is maximized. |
FEIPING NIE et. al. |
| 2008 | 6 | Simulation-Based Approach To General Game Playing IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe a GGP agent that instead uses a Monte Carlo/UCT simulation technique for action selection, an approach recently popularized in computer Go. |
Hilmar Finnsson; Yngvi Björnsson; |
| 2008 | 7 | Lifted First-Order Belief Propagation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose the first lifted version of a scalable probabilistic inference algorithm, belief propagation (loopy or not). |
Parag Singla; Pedro Domingos; |
| 2008 | 8 | Importance Of Semantic Representation: Dataless Classification IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Dataless Classification, a learning protocol that uses world knowledge to induce classifiers without the need for any labeled data. |
Ming-Wei Chang; Lev Ratinov; Dan Roth; Vivek Srikumar; |
| 2008 | 9 | Landmarks Revisited IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel approach for using landmarks in planning by deriving a pseudo-heuristic and combining it with other heuristics in a search framework. |
Silvia Richter; Malte Helmert; Matthias Westphal; |
| 2008 | 10 | Lifted Probabilistic Inference With Counting Formulas IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new lifted inference algorithm, C-FOVE, that not only handles counting formulas in its input, but also creates counting formulas for use in intermediate potentials. |
Brian Milch; Luke S. Zettlemoyer; Kristian Kersting; Michael Haimes; Leslie Pack Kaelbling; |
| 2008 | 11 | Determining Possible And Necessary Winners Under Common Voting Rules Given Partial Orders IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Usually a voting rule or correspondence requires agents to give their preferences as linear orders. However, in some cases it is impractical for an agent to give a linear order … |
Lirong Xia; Vincent Conitzer; |
| 2008 | 12 | AnalogySpace: Reducing The Dimensionality Of Common Sense Knowledge IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present AnalogySpace, which accomplishes this by forming the analogical closure of a semantic network through dimensionality reduction. |
Robyn Speer; Catherine Havasi; Henry Lieberman; |
| 2008 | 13 | Using Wiktionary For Computing Semantic Relatedness IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce Wiktionary as an emerging lexical semantic resource that can be used as a substitute for expert-made resources in AI applications. |
Torsten Zesch; Christof Müller; Iryna Gurevych; |
| 2008 | 14 | Linking Social Networks On The Web With FOAF: A Semantic Web Case Study IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a study of the intersection of FOAF data found in many online social networks. |
Jennifer Golbeck; Matthew Rothstein; |
| 2008 | 15 | Learning Grasp Strategies With Partial Shape Information IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an approach to grasping that estimates the stability of different grasps, given only noisy estimates of the shape of visible portions of an object, such as that obtained from a depth sensor. |
Ashutosh Saxena; Lawson L.S. Wong; Andrew Y. Ng; |
| 2007 | 1 | Coordinating Hundreds Of Cooperative, Autonomous Vehicles In Warehouses IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The Kiva warehouse management system creates a new paradigm for pick-pack-and-ship warehouses that significantly improves worker productivity. The Kiva system uses movable storage … |
Peter Wurman; Raffaello D’Andrea; Mick Mountz; |
| 2007 | 2 | Theta*: Any-Angle Path Planning On Grids IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Theta*, a variant of A*, that propagates information along grid edges without constraining the paths to grid edges. |
Alex Nash; Kenny Daniel; Sven Koenig; Ariel Felner; |
| 2007 | 3 | Transferring Naive Bayes Classifiers For Text Classification IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel transfer-learning algorithm for text classification based on an EM-based Naive Bayes classifier. |
Wenyuan Dai; Gui-Rong Xue; Qiang Yang; Yong Yu; |
| 2007 | 4 | Near-optimal Observation Selection Using Submodular Functions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we survey recent advances in systematically exploiting this submodularity property to efficiently achieve near-optimal observation selections, under complex constraints. |
Andreas Krause; Carlos Guestrin; |
| 2007 | 5 | Mapping And Revising Markov Logic Networks For Transfer Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a complete MLN transfer system that first autonomously maps the predicates in the source MLN to the target domain and then revises the mapped structure to further improve its accuracy. |
Lilyana Mihalkova; Tuyen Huynh; Raymond J. Mooney; |
| 2007 | 6 | Automatic Algorithm Configuration Based On Local Search IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a local search approach for algorithm configuration and prove its convergence to the globally optimal parameter configuration. |
Frank Hutter; Holger Hoos; Thomas Stuetzle; |
| 2007 | 7 | Joint Inference In Information Extraction IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a joint approach to information extraction, where segmentation of all records and entity resolution are performed together in a single integrated inference process. |
Hoifung Poon; Pedro Domingos; |
| 2007 | 8 | SUNNY: A New Algorithm For Trust Inference In Social Networks Using Probabilistic Confidence Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a new approach that gives an explicit probabilistic interpretation for confidence in social networks. |
Ugur Kuter; Jennifer Golbeck; |
| 2007 | 9 | Freebase: A Shared Database Of Structured General Human Knowledge IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Freebase is a practical, scalable, graph-shaped database of structured general human knowledge, inspired by Semantic Web research and collaborative data communities such as the … |
Kurt Bollacker; Robert Cook; Patrick Tufts; |
| 2007 | 10 | Domain-Independent Construction Of Pattern Database Heuristics For Cost-Optimal Planning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel way of constructing good patterns automatically from the specification of planning problem instances. |
Patrik Haslum; Adi Botea; Malte Helmert; Blai Bonet; Sven Koenig; |
| 2007 | 11 | Equilibria In Heterogeneous Nonmonotonic Multi-Context Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a general framework for multi-context reasoning which allows us to combine arbitrary monotonic and nonmonotonic logics. |
Gerhard Brewka; Thomas Eiter; |
| 2007 | 12 | Learning Graphical Model Structure Using L1-Regularization Paths IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we apply this technique to learn the structure of directed graphical models. |
Mark W. Schmidt; Alexandru Niculescu-Mizil; Kevin P. Murphy; |
| 2007 | 13 | Extracting Influential Nodes For Information Diffusion On A Social Network IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a method of efficiently estimating all those quantities on the basis of bond percolation and graph theory, and apply it to approximately solving the optimization problem under the greedy algorithm. |
Masahiro Kimura; Kazumi Saito; Ryohei Nakano.; |
| 2007 | 14 | Automated Online Mechanism Design And Prophet Inequalities IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Adopting the perspective of automated mechanism design, introduced by Conitzer and Sandholm, we develop algorithms that compute an optimal, or approximately optimal, online auction mechanism given access to this distributional knowledge. |
MohammadTaghi Hajiaghayi; Robert Kleinberg; Tuomas Sandholm; |
| 2007 | 15 | PLOW: A Collaborative Task Learning Agent IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue. |
JAMES ALLEN et. al. |
| 2006 | 1 | Corpus-based And Knowledge-based Measures Of Text Semantic Similarity IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method for measuring the semantic similarity of texts, using corpus-based and knowledge-based measures of similarity. |
Rada Mihalcea; Courtney Corley; Carlo Strapparava; |
| 2006 | 2 | WikiRelate! Computing Semantic Relatedness Using Wikipedia IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we present experiments on using Wikipedia for computing semantic relatedness and compare it to WordNet on various benchmarking datasets. |
Michael Strube Simone Paolo Ponzetto; |
| 2006 | 3 | Learning Systems Of Concepts With An Infinite Relational Model IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a nonparametric Bayesian model that discovers systems of related concepts. |
Charles Kemp; Joshua Tenenbaum; Thomas Griffiths; Takeshi Yamada; Naonori Ueda; |
| 2006 | 4 | Overcoming The Brittleness Bottleneck Using Wikipedia: Enhancing Text Categorization With Encyclopedic Knowledge IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present algorithms that can do just that. |
Evgeniy Gabrilovich; Shaul Markovitch; |
| 2006 | 5 | Mining Comparative Sentences And Relations IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose two novel techniques based on two new types of sequential rules to perform the tasks. |
Nitin Jindal; Bing Liu; |
| 2006 | 6 | Walk The Talk: Connecting Language, Knowledge, And Action In Route Instructions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Marco, an agent that follows free-form, natural language route instructions by representing and executing a sequence of compound action specifications that model which actions to take under which conditions. |
Matt MacMahon; Brian Stankiewicz; Benjamin Kuipers; |
| 2006 | 7 | Comparative Experiments On Sentiment Classification For Online Product Reviews IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We discuss a series of experiments with different machine learning algorithms in order to experimentally evaluate various trade-offs, using approximately 100K product reviews from the web. |
Hang Cui; Vibhu Mittal; Mayur Datar; |
| 2006 | 8 | Identification Of Joint Interventional Distributions In Recursive Semi-Markovian Causal Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide a necessary and sufficient graphical condition for the cases when the causal effect of an arbitrary set of variables on another arbitrary set can be determined uniquely from the available information, as well as an algorithm which computes the effect whenever this condition holds. |
Ilya Shpitser; Judea Pearl; |
| 2006 | 9 | Sound And Efficient Inference With Probabilistic And Deterministic Dependencies IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose MC-SAT, an inference algorithm that combines ideas from MCMC and satisfiability. |
Hoifung Poon; Pedro Domingos; |
| 2006 | 10 | Reinforcement Learning With Human Teachers: Evidence Of Feedback And Guidance With Implications For Learning Performance IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present findings from a human user study showing that people use the reward signal not only to provide feedback about past actions, but also to provide future directed rewards to guide subsequent actions. |
Andrea L. Thomaz; Cynthia Breazeal; |
| 2006 | 11 | Design And Implementation Of The CALO Query Manager IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We report on our experience in developing a query-answering system that integrates multiple knowledge sources. |
VINAY CHAUDHRI et. al. |
| 2006 | 12 | A Fast Decision Tree Learning Algorithm IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel, fast decision-tree learning algorithm that is based on a conditional independence assumption. |
Jiang Su; Harry Zhang; |
| 2006 | 13 | A Unified Cognitive Architecture For Physical Agents IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe Icarus, a cognitive architecture for physical agents that integrates ideas from a number of traditions, but that has been especially influenced by results from cognitive psychology. |
Pat Langley; Dongkyu Choi; |
| 2006 | 14 | Learning Blocking Schemes For Record Linkage IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a machine learning approach to automatically learn effective blocking schemes. |
Matthew Michelson and Craig A. Knoblock; |
| 2006 | 15 | Improved Bounds For Computing Kemeny Rankings IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we extend on this work by providing various improved bounding techniques. |
Vincent Conitzer; Andrew Davenport; Jayant Kalagnanam; |
| 2005 | 1 | Reducing Labeling Effort For Structured Prediction Tasks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new active learning paradigm which reduces not only how many instances the annotator must label, but also how difficult each instance is to annotate. |
Aron Culotta; Andrew McCallum; |
| 2005 | 2 | DL-Lite: Tractable Description Logics For Ontologies IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new Description Logic, called DL-Lite, specifically tailored to capture basic ontology languages, while keeping low complexity of reasoning. |
Diego Calvanese; Giuseppe De Giacomo; Domenico Lembo; Maurizio Lenzerini; Riccardo Rosati; |
| 2005 | 3 | Controversial Users Demand Local Trust Metrics: An Experimental Study On Epinions.com Community IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We argue, using computational experiments, that the existence of controversial users (a normal phenomena in societies) demands Local Trust Metrics, techniques able to predict the trustworthiness of an user in a personalized way, depending on the very personal view of the judging user. |
Paolo Massa; Paolo Avesani.; |
| 2005 | 4 | Unsupervised Activity Recognition Using Automatically Mined Common Sense IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A fundamental difficulty in recognizing human activities is obtaining the labeled data needed to learn models of those activities. |
Danny Wyatt; Matthai Philipose; Tanzeem Choudhury; |
| 2005 | 5 | Discriminative Training Of Markov Logic Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a discriminative approach to training MLNs, one which optimizes the conditional likelihood of the query predicates given the evidence ones, rather than the joint likelihood of all predicates. |
Parag Singla; Pedro Domingos; |
| 2005 | 6 | Learning To Transform Natural To Formal Languages IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a method for inducing transformation rules that map natural-language sentences into a formal query or command language. |
Rohit J. Kate; Yuk Wah Wong; Raymond J. Mooney; |
| 2005 | 7 | Performing Bayesian Inference By Weighted Model Counting IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe an efficient translation from Bayesian networks to weighted model counting, extend the best model-counting algorithms to weighted model counting, develop an efficient method for computing all marginals in a single counting pass, and evaluate the approach on computationally challenging reasoning problems. |
Tian Sang; Paul Beame; Henry Kautz; |
| 2005 | 8 | Anyone But Him: The Complexity Of Precluding An Alternative IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study in terms of complexity the vulnerability of preference aggregation to destructive control. |
Edith Hemaspaandra; Lane A. Hemaspaandra; Jörg Rothe; |
| 2005 | 9 | Large-Scale Localization From Wireless Signal Strength IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a novel technique for accurately estimating the locations of mobile devices and their wearers from wireless signal strengths. |
Julia Letchner; Dieter Fox; Anthony LaMarca; |
| 2005 | 10 | Exploiting Subjectivity Classification To Improve Information Extraction IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe an IE system that uses a subjective sentence classifier to filter its extractions. |
Ellen Riloff; Janyce Wiebe; William Phillips; |
| 2005 | 11 | Integrating Description Logics And Action Formalisms: First Results IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we perform a detailed investigation of how the choice of the DL influences the complexity of the standard reasoning tasks executability and projection in the corresponding action formalism. |
Franz Baader; Carsten Lutz; Maja Milicic; Ulrike Sattler; Frank Wolter; |
| 2005 | 12 | Mixed-Integer Programming Methods For Finding Nash Equilibria IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present, to our knowledge, the first mixed integer program (MIP) formulations for finding Nash equilibria in games (specifically, two-player normal form games). |
Tuomas Sandholm; Andrew Gilpin; Vincent Conitzer; |
| 2005 | 13 | Automatic Text Summarization Of Newswire: Lessons Learned From The Document Understanding Conference IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Since 2001, the Document Understanding Conferences have been the forum for researchers in automatic text summarization to compare methods and results on common test sets. |
Ani Nenkova; |
| 2005 | 14 | Unsupervised And Semi-Supervised Multi-class Support Vector Machines IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present new unsupervised and semi-supervised training algorithms for multi-class support vector machines based on semidefinite programming. |
Linli Xu; Dale Schuurmans; |
| 2005 | 15 | New Admissible Heuristics For Domain-Independent Planning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce two refinements of these heuristics: First, the additive hm heuristic which yields an admissible sum of hm heuristics using a partitioning of the set of actions. |
Patrik Haslum; Blai Bonet; Hector Geffner; |
| 2004 | 1 | Mining Opinion Features In Customer Reviews IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this project, we aim to summarize all the customer reviews of a product. |
Minqing Hu and Bing Liu; |
| 2004 | 2 | Learning And Inferring Transportation Routines IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through the community. |
Lin Liao; Dieter Fox; and Henry Kautz; |
| 2004 | 3 | Dynamic Programming For Partially Observable Stochastic Games IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop an exact dynamic programming algorithm for partially observable stochastic games (POSGs). |
Eric A. Hansen; Daniel S. Bernstein; and Shlomo Zilberstein; |
| 2004 | 4 | Just How Mad Are You? Finding Strong And Weak Opinion Clauses IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present the first experimental results classifying the strength of opinions and other types of subjectivity and classifying the subjectivity of deeply nested clauses. |
Theresa Wilson; Janyce Wiebe; and Rebecca Hwa; |
| 2004 | 5 | QUICKXPLAIN: Preferred Explanations And Relaxations For Over-Constrained Problems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this need, we define preferred explanations and relaxations based on user preferences between constraints and we compute them by a generic method which works for arbitrary CP, SAT, or DL solvers. |
Ulrich Junker; |
| 2004 | 6 | CMRadar: A Personal Assistant Agent For Calendar Management IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: One of the more compelling visions for agents research is the development of “personal assistant agents” that are tasked with making people and organizations more efficient by … |
Pragnesh Jay Modi; Manuela Veloso; Stephen F. Smith; and Jean Oh; |
| 2004 | 7 | Simple Search Methods For Finding A Nash Equilibrium IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present two simple search methods for computing a sample Nash equilibrium in a normal-form game: one for 2player games and one for n-player games. |
Ryan Porter; Eugene Nudelman; and Yoav Shoham; |
| 2004 | 8 | Metrics For Finite Markov Decision Processes IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The ultimate goal of this research is to efficiently compress and analyze continuous state space MDPs. |
Norm Ferns; Prakash Panangaden; and Doina Precup; |
| 2004 | 9 | Branching And Pruning: An Optimal Temporal POCL Planner Based On Constraint Programming IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a domain-independent formulation of temporal planning based on Constraint Programming is introduced that successfully combines a POCL branching scheme with powerful and sound pruning rules. |
Vincent Vidal and Héctor Geffner; |
| 2004 | 10 | Text Classification By Labeling Words IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a different approach. |
Bing Liu; Xiaoli Li; Wee Sun Lee; and Philip S. Yu; |
| 2004 | 11 | Machine Learning For Fast Quadrupedal Locomotion IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a machine learning approach to legged locomotion, with all training done on the physical robots. |
Nate Kohl and Peter Stone; |
| 2004 | 12 | Large-Scale Map-Making IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an abstraction method for postponing the growth in computation. |
Kurt Konolige; |
| 2004 | 13 | Interactive Information Extraction With Constrained Conditional Random Fields IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We apply this framework with two extensions: a constrained Viterbi decoding which finds the optimal field assignments consistent with the fields explicitly specified or corrected by the user; and a mechanism for estimating the confidence of each extracted field, so that low-confidence extractions can be highlighted. |
Trausti Kristjansson; Aron Culotta; Paul Viola; and Andrew McCallum; |
| 2004 | 14 | Extending CP-Nets With Stronger Conditional Preference Statements IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A logic of conditional preferences is defined, with a language which allows the compact representation of certain kinds of conditional preference statements, a semantics and a proof theory. |
Nic Wilson; |
| 2004 | 15 | Interleaving Temporal Planning And Execution In Robotics Domains IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a framework to integrate deliberative planning, plan repair and execution control in a dynamic environment with stringent temporal constraints. |
Solange Lemai and Félix Ingrand; |
| 2002 | 1 | FastSLAM: A Factored Solution To The Simultaneous Localization And Mapping Problem IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents FastSLAM, an algorithm that recursively estimates the full posterior distribution over robot pose and landmark locations, yet scales logarithmically with the number of landmarks in the map. |
Michael Montemerlo and Sebastian Thrun; Carnegie Mellon University; Daphne Koller and Ben Wegbreit; Stanford Universit; |
| 2002 | 2 | Content-Boosted Collaborative Filtering For Improved Recommendations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present an elegant and effective framework for combining content and collaboration. |
Prem Melville; Raymond J. Mooney; and Ramadass Nagarajan; University of Texas at Austin; |
| 2002 | 3 | ASSAT: Computing Answer Sets Of A Logic Program By SAT Solvers IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new translation from normal logic programs with constraints under the answer set semantics to propositional logic. |
Fangzhen Lin and Yuting Zhao; Hong Kong University of Science and Technology; |
| 2002 | 4 | A General Identification Condition For Causal Effects IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper concerns the assessment of the effects of actions or policy interventions from a combination of: (i) nonexperimental data, and (ii) substantive assumptions. |
Jin Tian and Judea Pearl; University of California; Los Angeles; |
| 2002 | 5 | Experiences With A Mobile Robotic Guide For The Elderly IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this research is to investigate the feasibility of assisting elderly people with cognitive and physical activity limitations through interactive robotic devices, thereby improving their quality of life. |
Michael Montemerlo; Joelle Pineau; Nicholas Roy; Sebastian Thrun; and Vandi Verma; |
| 2002 | 6 | Truthful Approximation Mechanisms For Restricted Combinatorial Auctions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We apply these techniques for several types of combinatorial auctions, obtaining truthful mechanisms with provable approximation ratios. We develop a set of techniques that allow constructing efficiently computable truthful mechanisms for combinatorial auctions in the special case where only the valuation is unknown by the mechanism (the single parameter case). |
Ahuva Mu’alem and Noam Nisan; The Hebrew University of Jerusalem vi; |
| 2002 | 7 | PROMPTDIFF: A Fixed-Point Algorithm For Comparing Ontology Versions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have developed the PromptDiff algorithm, which integrates different heuristic matchers for comparing ontology versions. |
Natalya F. Noy and Mark A. Musen; |
| 2002 | 8 | A POMDP Formulation Of Preference Elicitation Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe methods that exploit the special structure of preference elicitation to deal with parameterized belief states over the continuous state space, and gradient techniques for optimizing parameterized actions. |
Craig Boutilier; University of Toronto; |
| 2002 | 9 | Hierarchical Latent Class Models For Cluster Analysis IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose hierarchical latent class models as a framework where the local dependence problem can be addressed in a principled manner. |
Nevin L. Zhang; Hong Kong University of Science and Technology; |
| 2002 | 10 | Representing And Reasoning About Mappings Between Domain Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present sound and complete algorithms for the corresponding inference problems. |
Jayant Madhavan; University of Washington; Philip A. Bernstein; Microsoft Research; Pedro Domingos and Alon Y. Halevy; University of Washington; |
| 2002 | 11 | Language Modeling For Soft Keyboards IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe how language models, combined with models of pen placement, can be used to significantly reduce the error rate of soft keyboard usage, by allowing for cases in which a key press is outside of a key boundary. |
Joshua Goodman and Gina Venolia; Microsoft Research; Keith Steury; Microsoft Corporation; Chauncey Parker; University of Washington; |
| 2002 | 12 | Reinforcement Learning Of Coordination In Cooperative Multi-Agent Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We report on an investigation of reinforcement learning techniques for the learning of coordination in cooperative multi-agent systems. |
Spiros Kapetanakis and Daniel Kudenko; University of York; |
| 2002 | 13 | Structural Extension To Logistic Regression: Discriminative Parameter Learning Of Belief Net Classifiers IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents empirical evidence that ELR works better than the standard "generative" approach in a variety of situations, especially in common situation where the BN-structure is incorrect. |
Russell Greiner; University of Alberta; Wei Zhou; University of Waterloo; |
| 2002 | 14 | An Adaptive Noise Mechanism For WalkSAT IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we characterise the impact of the noise setting on the behaviour of WalkSAT and introduce a simple adaptive noise mechanism for WalkSAT that does not require manual adjustment for different problem instances. |
Holger H. Hoos; University of British Columbia; |
| 2002 | 15 | Recognizing Multitasked Activities From Video Using Stochastic Context-Free Grammar IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present techniques for recognizing complex, multitasked activities from video. |
Darnell Moore; Texas Instruments; Irfan Essa; Georgia Institute of Technology; |
| 2000 | 1 | PROMPT: Algorithm And Tool For Automated Ontology Merging And Alignment IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have developed and implemented PROMPT, an algorithm that provides a semi-automatic approach to ontology merging and alignment. |
Natalya Fridman Noy and Mark Musen; |
| 2000 | 2 | Clustering With Instance-Level Constraints IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In experiments with a partitioning variant of COBWEB, we show marked improvements with surprisingly few constraints on three of four data sets. |
Kiri Wagstaff and Claire Cardie; |
| 2000 | 3 | Coordination For Multi-Robot Exploration And Mapping IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper addresses the problem of exploration and mapping of an unknown environment by multiple robots. |
Reid Simmons and David Apfelbaum; Carnegie Mellon University; Wolfram Burgard; University of Freiburg; Dieter Fox; Carnegie Mellon University; Mark Moors; University of Bonn; Sebastian Thrun and Håkan Younes; |
| 2000 | 4 | Learning Subjective Adjectives From Corpora IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper identifies strong clues of subjectivity using the results of a method for clustering words according to distributional similarity (Lin 1998), seeded by a small amount of detailed manual annotation. |
Janyce M. Wiebe; |
| 2000 | 5 | Class-Based Construction Of A Verb Lexicon IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to building a verb lexicon compatible with WordNet but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically construct lexical entries. |
Karin Kipper; Hoa Trang Dang; and Martha Palmer; University of Pennsylvania; |
| 2000 | 6 | Iterative Combinatorial Auctions: Theory And Practice IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce iBundle, the first iterative combinatorial auction that is optimal for a reasonable agent bidding strategy, in this case myopic best-response bidding. |
David C. Parkes and Lyle H. Ungar; University of Pennsylvania; |
| 2000 | 7 | Dynamic Ontologies On The Web IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present SHOE, a web-based knowledge representation language that supports multiple versions of ontologies. |
Jeff Heflin and James Hendler; University of Maryland; |
| 2000 | 8 | Appearance-Based Obstacle Detection With Monocular Color Vision IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new vision-based obstacle detection method for mobile robots. |
Iwan Ulrich and Illah Nourbakhsh; |
| 2000 | 9 | Boosted Wrapper Induction IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent work in machine learning for information extraction has focused on two distinct sub-problems: the conventional problem of filling template slots from natural language text, and the problem of wrapper induction, learning simple extraction procedures (“wrappers”) for highly structured text such as Web pages produced by CGI scripts. |
Dayne Freitag; Just Research; Nicholas Kushmerick; University College Dublin; |
| 2000 | 10 | The Chimaera Ontology Environment IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our work with ontologies and tool environments over the last few years, we have observed growing needs for automated support of two tasks: (1) merging multiple ontologies and (2) diagnosing (and evolving) ontologies. |
Deborah L. McGuinness and Richard Fikes; Stanford University; James Rice; CommerceOne; Steve Wilder; |
| 2000 | 11 | Making Rational Decisions Using Adaptive Utility Elicitation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new approach for making decisions based on limited utility information, and for targetting our utility elicitation process so as to lead to a good decision using a small number of questions. |
Urszula Chajewska; Daphne Koller; and Ronald Parr; |
| 2000 | 12 | Information Extraction With HMM Structures Learned By Stochastic Optimization IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper demonstrates that extraction accuracy strongly depends on the selection of structure, and presents an algorithm for automatically finding good structures by stochastic optimization. |
Dayne Freitag and Andrew McCallum; Just Research; |
| 2000 | 13 | Solving Combinatorial Auctions Using Stochastic Local Search IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we apply a new stochastic local search algorithm, Casanova, to this problem. |
Holger H. Hoos; University of British Columbia; Craig Boutilier; University of Toronto; |
| 2000 | 14 | Bayesian Fault Detection And Diagnosis In Dynamic Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new approach to this task, based on the framework of hybrid dynamic Bayesian networks (DBN). |
Uri Lerner; Ronald Parr; and Daphne Koller; Stanford University; Gautam Biswas; |
| 2000 | 15 | Decision-Theoretic, High-Level Agent Programming In The Situation Calculus IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a framework for robot programming, which allows the seamless integration of explicit agent programming with decision-theoretic planning. |
Craig Boutilier; Ray Reiter; and Mikhail Soutchanski; University of Toronto; Sebastian Thrun; |
| 1999 | 1 | Monte Carlo Localization: Efficient Position Estimation For Mobile Robots IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new, highly efficient algorithm for mobile robot localization, called Monte Carlo Localization. |
Dieter Fox; Carnegie Mellon University; Wolfram Burgard; University of Bonn; Frank Dellaert and Sebastian Thrun; |
| 1999 | 2 | Learning Dictionaries For Information Extraction By Multi-Level Bootstrapping IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a multi-level bootstrapping algorithm for building both the semantic lexicon and extraction patterns simultaneously. |
Ellen Riloff; University of Utah and Rosie Jones; |
| 1999 | 3 | Combining Collaborative Filtering With Personal Agents For Better Recommendations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper shows that a CF framework can be used to combine personal IF agents and the opinions of a community of users to produce better recommendations than either agents or users can produce alone. |
NATHANIEL GOOD et. al. |
| 1999 | 4 | Relational Learning Of Pattern-Match Rules For Information Extraction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a system, RAPIER, that takes pairs of sample documents and filled templates and induces pattern-match rules that directly extract fillers for the slots in the template. |
Mary Elaine Califf; and Raymond J. Mooney; University of Texas at Austin; |
| 1999 | 5 | A Simple, Fast, And Effective Rule Learner IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe SLIPPER, a new rule learner that generates rulesets by repeatedly boosting a simple, greedy, rule-builder. |
William W. Cohen and Yoram Singer; AT&T Labs – Research; |
| 1999 | 6 | Feature Selection For Ensembles IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present an ensemble feature selection approach that is based on genetic algorithms. |
David W. Opitz; University of Montana; |
| 1999 | 7 | Navigational Plans For Data Integration IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the problem of building data integration systems when the data sources are webs of data, rather than sets of relations. |
Marc Friedman; Alon Levy; and Todd Millstein; University of Washington; |
| 1999 | 8 | EMediator: A Next Generation Electronic Commerce Server IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: eMediator , a next generation electronic commerceserver, demonstrates ways in which AI, algorithmic support, game theoretic incentive engineering, and GUI design can jointly … |
Tuomas Sandholm; |
| 1999 | 9 | On The Undecidability Of Probabilistic Planning And Infinite-Horizon Partially Observable Markov Decision Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the computability of problems in probabilistic planning and partially observable infinite-horizon Markov decision processes. |
Omid Madani; University of Washington; Steve Hanks; Harlequin Inc; Anne Condon; University of Wisconsin; |
| 1999 | 10 | SMILE: Structural Modeling, Inference, And Learning Engine And GeNIe: A Development Environment For Graphical Decision-Theoretic Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: SMILE (Structural Modeling, Inference, and Learning Engine) is a fully portable library of C++ classes implementing graphical decision-theoretic methods, such as Bayesian networks and influence diagrams, directly amenable to inclusion in intelligent systems. |
Marek J. Druzdzel; University of Pittsburgh; |
| 1999 | 11 | A Policy Description Language IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce PDL, a simple but expressive language to specify policies. |
Jorge Lobo; Randeep Bhatia and Shamim Naqvi; Bell Labs; |
| 1999 | 12 | MailCat: An Intelligent Assistant For Organizing E-Mail IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: When one of MailCat’s predictions is correct, the effort required to file a message is reduced to a single button click. |
Richard B. Segal and Jeffrey O. Kephart; |
| 1999 | 13 | Towards Multidocument Summarization By Reformulation: Progress And Prospects IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. |
Kathleen R. McKeown; Judith L. Klavans; Vasileios Hatzivassiloglou; Regina Barzilay; and Eleazar Eskin; |
| 1999 | 14 | Selective Sampling For Nearest Neighbor Classifiers IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a lookahead algorithm for example selection and addresses the problem of active learning in the context of nearest neighbor classifiers. |
Michael Lindenbaum; Shaul Markovich; and Dmitry Rusakov; Technion – Israel Institute of Technology; |
| 1999 | 15 | A Framework For Recognizing Multi-Agent Action From Visual Evidence IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A framework for representing and visually recognizing complex multi-agent action is presented. |
Stephen S. Intille and Aaron F. Bobick; MIT Media Laboratory; |
| 1998 | 1 | The Dynamics Of Reinforcement Learning In Cooperative Multiagent Systems IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We examine some of the factors that can influence the dynamics of the learning process in such a setting. |
Caroline Claus; Craig Boutilier; |
| 1998 | 2 | Recommendation As Classification: Using Social And Content-Based Information In Recommendation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an inductive learning approach to recommendation that is able to use both ratings information and other forms of information about each artifact in predicting user preferences. |
Chumki Basu; Haym Hirsh; William Cohen; |
| 1998 | 3 | Learning To Extract Symbolic Knowledge From The World Wide Web IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of the research described here is to automatically create a computer understandable world wide knowledge base whose content mirrors that of the World Wide Web. |
MARK CRAVEN et. al. |
| 1998 | 4 | Boosting Combinatorial Search Through Randomization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a general method for introducing controlled randomization into complete search algorithms. |
Carla P. Gomes; Bart Selman; Henry Kautz; |
| 1998 | 5 | The Interactive Museum Tour-Guide Robot IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the software architecture of an autonomous tour-guide/tutor robot. |
WOLFRAM BURGARD et. al. |
| 1998 | 6 | Anytime Coalition Structure Generation With Worst Case Guarantees IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an algorithm that establishes a tight bound within this minimal amount of search, and show that any other algorithm would have to search strictly more. |
Tuomas Sandholm; Kate Larson; Martin Andersson; Onn Shehory; Fernando Tohmé; |
| 1998 | 7 | TRIPS: An Integrated Intelligent Problem-Solving Assistant IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe one particular integrated system we have developed that supports spoken-language dialogue to collaboratively solve planning problems. |
George Ferguson; James F. Allen; |
| 1998 | 8 | Bayesian Q-Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we adopt a Bayesian approach to maintaining this uncertain information. |
Richard Dearden; Nir Friedman; Stuart Russell; |
| 1998 | 9 | Learning To Classify Text From Labeled And Unlabeled Documents IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a theoretical argument showing that, under common assumptions, unlabeled data contain information about the target function. |
Kamal Nigam; Andrew McCallum; Sebastian Thrun; Tom Mitchell; |
| 1998 | 10 | OKBC: A Programmatic Foundation For Knowledge Base Interoperability IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we discuss technical design issues faced in the development of OKBC, highlight how OKBC improves upon GFP, and report on practical experiences in using it. |
Vinay K. Chaudhri; Adam Farquhar; Richard Fikes; Peter D. Karp; James P. Rice; |
| 1998 | 11 | Design Principles For Intelligent Environments IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes design criteria for creating highly embedded, interactive spaces that we call Intelligent Environments. |
Michael H. Coen; |
| 1998 | 12 | Adaptive Web Sites: Automatically Synthesizing Web Pages IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce our own approach to this broad challenge. |
Mike Perkowitz; Oren Etzioni; |
| 1998 | 13 | Probabilistic Frame-Based Systems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we provide a language that cleanly integrates these approaches, preserving the advantages of both. |
Daphne Koller; Avi Pfeffer; |
| 1998 | 14 | Information Extraction From HTML: Application Of A General Machine Learning Approach IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show how information extraction can be cast as a standard machine learning problem, and argue for the suitability of relational learning in solving it. |
Dayne Freitag; |
| 1998 | 15 | Extending Graphplan To Handle Uncertainty And Sensing Actions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe SGP, a descendant of Graphplan that solves contingent planning problems. |
Daniel S. Weld; Corin R. Anderson; David E. Smith; |
| 1997 | 1 | Using CSP Look-Back Techniques To Solve Real-World SAT Instances IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We report on the performance of an enhanced version of the "Davis-Putnam" (DP) proof procedure for propositional satisfiability (SAT) on large instances derived from realworld problems in planning, scheduling, and circuit diagnosis and synthesis. |
Roberto J. Bayardo Jr.; Robert C. Schrag; |
| 1997 | 2 | Statistical Parsing With A Context-Free Grammar And Word Statistics IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence. |
Eugene Charniak; |
| 1997 | 3 | Evidence For Invariants In Local Search IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present two statistical measures of the local search process that allow one to quickly find the optimal noise settings. |
David McAllester; Bart Selman; Henry Kautz; |
| 1997 | 4 | Modeling Emotions And Other Motivations In Synthetic Agents IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Cathexis, a distributed, computational model which offers an alternative approach to model the dynamic nature of different affective phenomena, such as emotions, moods and temperaments, and provides a flexible way of modeling their influence on the behavior of synthetic autonomous agents. |
Juan D. Velásquez; |
| 1997 | 5 | An Empirical Evaluation Of Bagging And Boosting IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we evaluate these methods using both neural networks and decision trees as our classification algorithms. |
Richard Maclin; David Opitz; |
| 1997 | 6 | Causal Theories Of Action And Change IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We define a mathematically simple language for expressing knowledge of this kind and describe a general approach to formalizing action domains in it. |
Norman McCain; Hudson Turner; |
| 1997 | 7 | Lessons In Neural Network Training: Overfitting May Be Harder Than Expected IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that the optimal solution is typically not found. |
Steve Lawrence; C. Lee Giles; Ah Chung Tsoi; |
| 1997 | 8 | A Robust And Fast Action Selection Mechanism For Planning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we develop one such algorithm by looking at planning as real time search. |
Blai Bonet; Gábor Loerincs; Héctor Geffner; |
| 1997 | 9 | P-classIC: A Tractable Probablistic Description Logic IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present P-classIC, a probabilistic version of the description logic classIC. |
Daphne Koller; Alon Levy; Avi Pfeffer; |
| 1997 | 10 | Multi-Document Summarization By Graph Search And Matching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a new method for summarizing similarities and differences in a pair of related documents using a graph representation for text. |
Inderjeet Mani; Eric Bloedorn; |
| 1997 | 11 | Model Minimization In Markov Decision Processes IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide an algorithm for finding the coarsest homogeneous reflnement of any partition of the state space of an MDP. |
Thomas Dean; Robert Givan; |
| 1997 | 12 | Layered Learning In Multiagent Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: My thesis will focus on learning in this particularly complex class of multiagent domains. |
Peter Stone; |
| 1997 | 13 | Agent Architectures For Flexible, Practical Teamwork IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Teamwork in complex, dynamic, multi-agent domains mandates highly flexible coordination and communication. Simply fitting individual agents with precomputed coordination plans … |
Milind Tambe; |
| 1997 | 14 | Active Learning With Committees For Text Categorization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe an active learning method that uses a committee of learners to reduce the number of training examples required for learning. |
Ray Liere; Prasad Tadepalli; |
| 1997 | 15 | If At First You Don’t Succeed IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: If at First You Don’t Succeed… |
Kentaro Toyama; Gregory D. Hager; |
| 1996 | 1 | Pushing The Envelope: Planning, Propositional Logic, And Stochastic Search IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By combining a general, stochastic search algorithm and appropriate problem encodings based on propositional logic, we are able to solve hard planning problems many times faster than the best current planning systems. |
Henry Kautz; Bart Selman; |
| 1996 | 2 | Learning To Parse Database Queries Using Inductive Logic Programming IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents recent work using the CHILL parser acquisition system to automate the construction of a natural-language interface for database queries. |
John M. Zelle; Raymond J. Mooney; |
| 1996 | 3 | A Model-Based Approach To Reactive Self-Configuring Systems IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes Livingstone, an implemented kernel for a model-based reactive self-configuring autonomous system. |
Brian C. Williams; P. Pandurang Nayak; |
| 1996 | 4 | Estimating The Absolute Position Of A Mobile Robot Using Position Probability Grids IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the position probability grid approach to estimating the robot’s absolute position and orientation in a metric model of the environment. |
Wolfram Burgard; Dieter Fox; Daniel Hennig; Timo Schmidt; |
| 1996 | 5 | Integrating Grid-Based And Topological Maps For Mobile Robot Navigation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes an approach that integrates both paradigms: grid-based and topological. |
Sebastian Thrun; Arno Bücken; |
| 1996 | 6 | Generalized Arc Consistency For Global Cardinality Constraint IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present an efficient way of implementing generalized arc consistency for a gcc. |
Jean-Charles Régin; |
| 1996 | 7 | Tree-Bank Grammars IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The primary purpose of this paper is to show that the common wisdom is wrong. |
Eugene Charniak; |
| 1996 | 8 | Learning Trees And Rules With Set-Valued Features IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: W e propose an extension of the feature-vector representation that allows the value of a feature to be a set of strings; for instance, to represent a small white and black dog with the nominal features size and species and the set-valued feature color, one might use a feature vector with size=small, species=canis-familiaris and color={ white, black}. |
William W. Cohen; |
| 1996 | 9 | Lazy Decision Trees IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a lazy decision tree algorithm-LazyDT-that conceptually constructs the "best" decision tree for each test instance. |
Jerome H. Friedman; Ron Kohavi; Yeogirl Yun; |
| 1996 | 10 | What Is Planning In The Presence Of Sensing? IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop and motivate a specification within the situation calculus of conditional and iterative plans over domains that include binary sensing actions. |
Hector J. Levesque; |
| 1996 | 11 | Query-Answering Algorithms For Information Agents IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the architecture and query-answering algorithms used in the Information Manifold, an implemented information gathering system that provides uniform access to structured information sources on the World-Wide Web. |
Alon Y. Levy; Anand Rajaraman; Joann J. Ordille; |
| 1996 | 12 | Identifying And Eliminating Mislabeled Training Instances IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new approach to identifying and eliminating mislabeled training instances. |
Carla E. Brodley; Mark A. Friedl; |
| 1996 | 13 | Planning For Temporally Extended Goals IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose viewing goals as specifiying desirable sequences of states, and a plan to be correct if its execution yields one of these desirable sequences. |
Fahiem Bacchus; Froduald Kabanza; |
| 1996 | 14 | Declarative Camera Control For Automatic Cinematography IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe several of the principles of cinematography and show how they can be formalized into a declarative language, called the Declarative Camera Control Language (DCCL). |
DAVID B. CHRISTIANSON et. al. |
| 1996 | 15 | Building Classifiers Using Bayesian Networks IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we examine and evaluate approaches for inducing classifiers from data, based on recent results in the theory of learning Bayesian networks. |
Nir Friedman; Moises Goldszmidt; |
| 1994 | 1 | Noise Strategies For Improving Local Search IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will compare three such mechanisms: simulated annealing, random noise, and a strategy called "mixed random walk". |
Bart Selman; Henry A. Kautz; Bram Cohen; |
| 1994 | 2 | HTN Planning: Complexity And Expressivity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes how the complexity of HTN planning varies with various conditions on the task networks. |
Kutluhan Erol; James Hendler; Dana S. Nau; |
| 1994 | 3 | A Filtering Algorithm For Constraints Of Difference In CSPs IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a new filtering algorithm for these constraints is presented. |
Jean-Charles Régin; |
| 1994 | 4 | Acting Optimally In Partially Observable Stochastic Domains IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe the partially observable Markov decision process (POMDP) approach to finding optimal or near-optimal control strategies for partially observable stochastic environments, given a complete model of the environment. |
Anthony R. Cassandra; Leslie Pack Kaelbling; Michael L. Littman; |
| 1994 | 5 | Some Advances In Transformation-Based Part Of Speech Tagging IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe a number of extensions to this rule-based tagger. |
Eric Brill; |
| 1994 | 6 | Collaborative Interface Agents IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a framework for multi-agent collaboration and discuss results of a working prototype, based on learning agents for electronic mail. |
Yezdi Lashkari; Max Metral; Pattie Maes; |
| 1994 | 7 | Building A Large-Scale Knowledge Base For Machine Translation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One of the hypotheses being tested in the PANGLOSS machine translation project is whether or not these resources can be semi-automatically acquired on a very large scale. |
Kevin Knight; Steve K. Luk; |
| 1994 | 8 | Learning To Coordinate Without Sharing Information IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to handle the changing requirements of continuous and dynamic environments, we propose learning as a means to provide additional possibilities for effective coordination. |
Sandip Sen; Mahendra Sekaran; John Hale; |
| 1994 | 9 | ChatterBots, TinyMuds, And The Turing Test: Entering The Loebner Prize Competition IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the development of one such Turing System, including the technical design of the program and its performance on the first three Loebner Prize competitions. |
Michael L. Mauldin; |
| 1994 | 10 | Topological Mapping For Mobile Robots Using A Combination Of Sonar And Vision Sensing IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Results described in this paper show that our robot is able to perform place recognition without having to move through a sequence of places, as is the case with most currently implemented systems. |
David Kortenkamp; Terry Weymouth; |
| 1994 | 11 | Experimental Results On The Application Of Satisfiability Algorithms To Scheduling Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We suggest that the best algorithms for this problem class will probably be hill-climbing algorithms that incorporate some sort of forward checking. |
James M. Crawford; Andrew B. Baker; |
| 1994 | 12 | Guardian: A Prototype Intelligent Agent For Intensive-Care Monitoring IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A surgical intensive care unit (ICU) is a challenging monitoring environment. The multitude of monitored variables, the high frequency of alarms, and the severity of likely … |
BARBARA HAYES-ROTH et. al. |
| 1994 | 13 | Automated Postediting Of Documents IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For the case of MT-generated text, we argue for the construction of postediting modules that are portable across MT systems, as an alternative to hardcoding improvements inside any one system. |
Kevin Knight; Ishwar Chander; |
| 1994 | 14 | Solution Reuse In Dynamic Constraint Satisfaction Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a method for reusing any previous solution and producing a new one by local changes on the previous one. |
Gerard Verfaillie; Thomas Schiex; |
| 1994 | 15 | Coalition, Cryptography, And Stability: Mechanisms For Coalition Formation In Task Oriented Domains IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple coalition formation mechanism that uses cryptographic techniques for subadditive Task Oriented Domains. |
Gilad Zlotkin; Jeffrey S. Rosenschein; |
| 1993 | 1 | An Implementation Of The Contract Net Protocol Based On Marginal Cost Calculations IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a formalization of the bidding and awarding decision process that was left undefined in the original contract net task allocation protocol. |
Tuomas Sandholm; |
| 1993 | 2 | Automatically Constructing A Dictionary For Information Extraction Tasks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response to this problem, we developed a system called AutoSlog that automatically builds a domain-specific dictionary of concepts for extracting information from text. |
Ellen Riloff; |
| 1993 | 3 | The Breakout Method For Escaping From Local Minima IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe an iterative improvement algorithm, called Breakout, that can escape from local minima. |
Paul Morris; |
| 1993 | 4 | Arc-Consistency And Arc-Consistency Again IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new algorithm, AC-6, which keeps the optimal worst-case time complexity of AC-4 while working out the drawback of space complexity. |
Christian Bessière; Marie-Odile Cordier; |
| 1993 | 5 | Learning Interface Agents IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Interface agents are computer programs that employ Artificial Intelligence techniques in order to provide assistance to a user dealing with a particular computer application. |
Pattie Maes; Robyn Kozierok; |
| 1993 | 6 | The Frame Problem And Knowledge-Producing Actions IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a solution to the frame problem for knowledge-producing actions. |
Richard B. Scherl; Hector J. Levesque; |
| 1993 | 7 | The Paradoxical Success Of Fuzzy Logic IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates the question of which aspects of fuzzy logic are essential to its practical usefulness. |
Charles Elkan; |
| 1993 | 8 | Generating Explanations Of Device Behavior Using Compositional Modeling And Causal Ordering IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Generating explanations of device behavior is a long-standing goal of AI research in reasoning about physical systems. |
Patrice O. Gautier; Thomas R. Gruber; |
| 1993 | 9 | Towards An Understanding Of Hill-Climbing Procedures For SAT IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By the introduction of some new variants of these procedures, we provide strong experimental evidence to support our conjecture that neither greediness nor randomness is important in these procedures. |
Ian P. Gent; Toby Walsh; |
| 1993 | 10 | Planning With Deadlines In Stochastic Domains IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide a method, based on the theory of Markov decision problems, for efficient planning in stochastic domains. |
Thomas Dean; Leslie Pack Kaelbling; Jak Kirman; Ann Nicholson; |
| 1993 | 11 | Polly: A Vision-Based Artificial Agent IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper I will describe Polly, a low cost vision-based robot that gives primitive tours. |
Ian Horswill; |
| 1993 | 12 | Equations For Part-of-Speech Tagging IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We derive from first principles the basic equations for a few of the basic hidden-Markov-model word taggers as well as equations for other models which may be novel (the descriptions in previous papers being too spare to be sure). |
Eugene Charniak; Curtis Hendrickson; Neil Jacobson; Mike Perkowitz; |
| 1993 | 13 | Complexity Analysis Of Real-Time Reinforcement Learning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of reaching a goal state in deterministic domains. |
Sven Koenig; Reid G. Simmons; |
| 1993 | 14 | Slack-Based Heuristics For Constraint Satisfaction Scheduling IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we define and empirically evaluate new heuristics for solving the job shop scheduling problem with non-relaxable time windows. |
Stephen F. Smith; Cheng-Chung Cheng; |
| 1993 | 15 | An Empirical Study Of Greedy Local Search For Satisfiability Testing IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the results of numerous experiments we have performed with GSAT, in order to improve our understanding of its capabilities and limitations. |
Bart Selman; Henry A. Kautz; |
| 1992 | 1 | The Feature Selection Problem: Traditional Methods And A New Algorithm IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We review and analyze past approaches to feature selection and note their strengths and weaknesses. |
Kenji Kira; Larry A. Rendell; |
| 1992 | 2 | An Analysis Of Bayesian Classifiers IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present an average-case analysis of the Bayesian classifier, a simple induction algorithm that fares remarkably well on many learning tasks. |
Pat Langley; Wayne Iba; Kevin Thompson; |
| 1992 | 3 | Hard And Easy Distributions Of SAT Problems IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We report results from large-scale experiments in satisfiability testing. |
David Mitchell; Bart Selman; Hector Levesque; |
| 1992 | 4 | ChiMerge: Discretization Of Numeric Attributes IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes ChiMerge, a general, robust algorithm that uses the x2 statistic to discretize (quantize) numeric attributes. |
Randy Kerber; |
| 1992 | 5 | A New Method For Solving Hard Satisfiability Problems IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a greedy local search procedure called GSAT for solving propositional satisfiability problems. |
Bart Selman; Hector Levesque; David Mitchell; |
| 1992 | 6 | Integrating Planning And Reacting In A Heterogeneous Asynchronous Architecture For Controlling Real-World Mobile Robots IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a heterogeneous, asynchronous architecture for controlling autonomous mobile robots which is capable of controlling a robot performing multiple tasks in real time in noisy, unpredictable environments. |
Erann Gat; |
| 1992 | 7 | Reinforcement Learning With Perceptual Aliasing: The Perceptual Distinctions Approach IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces the predictive distinctions approach to compensate for perceptual aliasing caused from incomplete perception of the world. |
Lonnie Chrisman; |
| 1992 | 8 | On The Synthesis Of Useful Social Laws For Artificial Agent Societies (Preliminary Report) IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a general model of social law in a computational system, and investigate some of its properties. |
Yoav Shoham; Moshe Tennenholtz; |
| 1992 | 9 | The Attribute Selection Problem In Decision Tree Generation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address the problem of selecting an attribute and some of its values for branching during the top-down generation of decision trees. |
Usama M. Fayyad; Keki B. Irani; |
| 1992 | 10 | Adapting Bias By Gradient Descent: An Incremental Version Of Delta-Bar-Delta IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I present a new algorithm, the Incremental Delta-Bar-Delta (IDBD) algorithm, for the learning of appropriate biases based on previous learning experience. |
Richard S. Sutton; |
| 1992 | 11 | A Personal Learning Apprentice IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present one such personal learning apprentice, called CAP, which assists in managing a meeting calendar. |
Lisa Dent; Jesus Boticario; Tom Mitchell; David Zabowski; John McDermott; |
| 1992 | 12 | Computing Least Common Subsumers In Description Logics IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a new operation for description logics: computing the "least common subsumer" of a pair of descriptions. |
William W. Cohen; Alex Borgida; Haym Hirsh; |
| 1992 | 13 | Artificial Intelligence And Molecular Biology IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The twin goals of artificial intelligence research are to understand the computational mechanisms underlying human-like thought and behavior, and to design and synthesize comparable machines. |
Lawrence Hunter; |
| 1992 | 14 | Learning Relations By Pathfinding IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method, called relational pathfinding, which has proven highly effective in escaping local maxima and crossing local plateaus. |
Bradley L. Richards; Raymond J. Mooney; |
| 1992 | 15 | Reinforcement Learning With A Hierarchy Of Abstract Models IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I present H-DYNA (Hierarchical DY NA), an extension to Sutton’s DYNA architecture that is able to learn such a hierarchy of abstract models. |
Satinder P. Singh; |
| 1991 | 1 | Learning With Many Irrelevant Features IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Experimental studies are presented that compare FOCUS to the ID3 and FRINGE algorithms. |
Hussein Almuallim; Thomas G. Dietterich; |
| 1991 | 2 | Automatic Programming Of Behavior-Based Robots Using Reinforcement Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a general approach for automatically programming a behavior-based robot. |
Sridhar Mahadevan; Jonathan Connell; |
| 1991 | 3 | Systematic Nonlinear Planning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a simple, sound, complete, and systematic algorithm for domain independent STRIPS planning. |
David McAllester; David Rosenblitt; |
| 1991 | 4 | Combining Qualitative And Quantitative Constraints In Temporal Reasoning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a general model for temporal reasoning, capable of handling both qualitative and quantitative information. |
Itay Meiri; |
| 1991 | 5 | Eliminating Interchangeable Values In Constraint Satisfaction Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper develops a concept of interchangeability of CSP values. |
Eugene C. Freuder; |
| 1991 | 6 | Error-Correcting Output Codes: A General Method For Improving Multiclass Inductive Learning Programs IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper compares these three approaches to a new technique in which BCH error-correcting codes are employed as a distributed output representation. |
Thomas G. Dietterich; Ghulum Bakiri; |
| 1991 | 7 | Integrating Metric And Qualitative Temporal Reasoning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we demonstrate how metric and Allen-style constraint networks can be integrated in a constraint-based reasoning system. |
Henry A. Kautz; Peter B. Ladkin; |
| 1991 | 8 | The Clarke Tax As A Consensus Mechanism Among Automated Agents IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper examines how the Clarke tax could be used as an effective "preference revealer" in the domain of automated agents, reducing the need for explicit negotiation. |
Eithan Ephrati; Jeffrey S. Rosenschein; |
| 1991 | 9 | Rule Learning By Searching On Adapted Nets IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The algorithm is able to deal with both single-layer and muti-layer networks, and can learn both confirming and disconfirming rules. |
LiMin Fu; |
| 1991 | 10 | Preferential Semantics For Goals IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This semantic account provides a criterion for verifying the design of goal-based planning strategies, thus providing a new framework for knowledge-level analysis of planning systems. |
Michael P. Wellman; Jon Doyle; |
| 1991 | 11 | A Complexity Analysis Of Cooperative Mechanisms In Reinforcement Learning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Reinforcement learning algorithms, when used to solve multi-stage decision problems, perform a kind of online (incremental) search to find an optimal decision policy. |
Steven D. Whitehead; |
| 1991 | 12 | Focusing On Probable Diagnoses IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper analyzes the diverse origins of this combinatorial explosion and outlines strategies to cope with each one. |
Johan de Kleer; |
| 1991 | 13 | Programming Robots Using Reinforcement Learning And Teaching IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a general approach to making robots which can improve their performance from experiences as well as from being taught. |
Long-Ji Lin; |
| 1991 | 14 | Direct Transfer Of Learned Information Among Neural Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates an analogous problem: how to use information from one neural network to help a second network learn a related task. |
Lorien Y. Pratt; Jack Mostow; Candace A. Kamm; |
| 1991 | 15 | Knowledge Compilation Using Horn Approximations IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new approach to developing fast and efficient knowledge representation systems. |
Bart Selman; Henry Kautz; |
| 1990 | 1 | On Acting Together IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a formal definition of what it could mean for a group to jointly commit to a common goal, and explore how these joint commitments relate to the individual commitments of the team members. |
Hector J. Levesque; Philip R. Cohen; José H.T. Nunes; |
| 1990 | 2 | Dynamic Constraint Satisfaction Problems IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we formalize this notion as a dynamic constraint satisfaction problem that uses two types of constraints. |
Sanjay Mittal; Brian Falkenhainer; |
| 1990 | 3 | Learning To Coordinate Behaviors IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe an algorithm which allows a behavior-based robot to learn on the basis of positive and negative feedback when to activate its behaviors. |
Pattie Maes; Rodney A. Brooks; |
| 1990 | 4 | Refinement Of Approximate Domain Theories By Knowledge-Based Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Standard algorithms for explanation-based learning require complete and correct knowledge bases. The KBANN system relaxes this constraint through the use of empirical learning … |
Geoffrey G. Towell; Jude W. Shavlik; Michiel O. Noordewier; |
| 1990 | 5 | Introducing The Tileworld: Experimentally Evaluating Agent Architectures IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a system called Tileworld, which consists of a simulated robot agent and a simulated environment which is both dynamic and unpredictable. |
Martha E. Pollack; Marc Ringuette; |
| 1990 | 6 | Reasoning About Qualitative Temporal Information IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address two related reasoning tasks that arise in these algebras: Given (possibly indefinite) knowledge of the relationships between some intervals or points, (1) find one or more scenarios that are consistent with the information provided, and (2) find all the feasible relations between every pair of intervals or points. |
Peter van Beek; |
| 1990 | 7 | Two Views Of Belief: Belief As Generalized Probability And Belief As Evidence IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We argue that there are (at least) two useful and quite different ways of understanding belief functions. |
Joseph Y. Halpern; Ronald Fagin; |
| 1990 | 8 | Abductive And Default Reasoning: A Computational Core IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we explore abduction tasks similar to that of the ATMS, but which return relatively small answers. |
Bart Selman; Hector J. Levesque; |
| 1990 | 9 | A Qualitative Model For Space IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we describe a systematic representation that builds spatial maps based on local qualitative relations between objects. |
Amitabha Mukerjee; Gene Joe; |
| 1990 | 10 | Changing The Rules: A Comprehensive Approach To Theory Refinement IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a comprehensive approach to automatic theory refinement. |
Dirk Ourston; Raymond J. Mooney; |
| 1990 | 11 | Complexity Of K-Tree Structured Constraint Satisfaction Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Trees have played a key role in the study of constraint satisfaction problems because problems with tree structure can be solved efficiently. |
Eugene C. Freuder; |
| 1990 | 12 | Truth Maintenance IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper discusses the functionality of truth maintenance systems and compares various existing algorithms. |
David McAllester; |
| 1990 | 13 | Anytime Synthetic Projection: Maximizing The Probability Of Goal Satisfaction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a projection algorithm for incremental control rule synthesis. |
Mark Drummond; John Bresinai; |
| 1990 | 14 | Symbolic Probabilistic Inference In Belief Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The Symbolic Probabilistic Inference (SPI) Algorithm [D’Ambrosio, 1989] provides an efficient framework for resolving general queries on a belief network. |
Ross D. Shachter; Bruce D’Ambrosio; Brendan A. Del Favero; |
| 1990 | 15 | Learning Abstraction Hierarchies For Problem Solving IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper identifies a criterion for selecting useful abstractions, describes a tractable algorithm for generating them, and empirically demonstrates that the abstractions reduce search. |
Craig A. Knoblock; |
| 1988 | 1 | An Analysis Of Time-Dependent Planning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a framework for exploring issues in time-dependent planning: planning in which the time available to respond to predicted events varies, and the decision making required to formulate effective responses is complex. |
Thomas Dean; Mark Boddy; |
| 1988 | 2 | Quantitative Results Concerning The Utility Of Explanation-Based Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The system produces useful control knowledge by actively searching for "good" explanations –explanations that can be profitably employed to control problem solving. |
Steven Minton; |
| 1988 | 3 | Reasoning About Action Using A Possible Models Approach IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Ginsberg and Smith [6, 7] propose a new method for reasoning about action, which they term a possible worlds approach (PWA). |
Marianne Winslett; |
| 1988 | 4 | Bayesian Classification IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a Bayesian technique for unsupervised classification of data and its computer implementation, AutoClass. |
Peter Cheeseman; Matthew Self; Jim Kelly; Will Taylor; Don Freeman; |
| 1988 | 5 | Belief Maintenance In Dynamic Constraint Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a constraint network formulation of belief maintenance in dynamically changing environments. |
Rina Dechter; Avi Dechter; |
| 1988 | 6 | Integrating Planning, Execution And Monitoring IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: IPEM, for Integrated Planning, Execution and Monitoring, provides a simple, clear and well defined framework to integrate these processes. |
Jose A. Ambros-lngerson; Sam Steel; |
| 1988 | 7 | Reasoning About Evidence In Causal Explanations IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a system that solves a new problem by recalling a previous, similar problem and modifying its solution to fit the current problem. |
Phyllis Koton; |
| 1988 | 8 | A Deductive Pattern Matcher IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the design of a pattern matcher for a knowledge representation system called LOOM. |
Robert M. MacGregor; |
| 1988 | 9 | Reasoning Under Varying And Uncertain Resource Constraints IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe the use of decision-theory to optimize the value of computation under uncertain and varying resource limitations. |
Eric J. Horvitz; |
| 1988 | 10 | Resolving Goal Conflicts Via Negotiation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide a model of goal conflict resolution through negotiation implemented in the PERSUADER, a program that resolves labor disputes. |
Kaffa P. Sycara; |
| 1988 | 11 | Knowledge-Base Reduction: A New Approach To Checking Knowledge Bases For Inconsistency And Redundancy IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new approach, called knowledge-base reduction, to the problem of checking knowledge bases for inconsistency and redundancy. |
Allen Ginsberg; |
| 1988 | 12 | Using Incomplete Quantitative Knowledge In Qualitative Reasoning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method for incrementally exploiting incomplete quantitative knowledge, by using it to refine the predictions of a qualitative reasoner. |
Benjamin Kuipers; Daniel Berleant; |
| 1988 | 13 | A Robust, Qualitative Method For Robot Spatial Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a qualitative method for a mobile robot to explore an unknown environment and learn a map, which can be robust in the face of various possible errors in the real world. |
Benjamin J. Kuipers; Yung-Tai Byun; |
| 1988 | 14 | Goals As Parallel Program Specifications IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a formalism, called Gapps, that allows a programmer to specify an agent’s behavior using symbolic goal-reduction rules that are compiled into an efficient parallel program. |
Leslie Pack Kaelbling; |
| 1988 | 15 | A Rearrangement Search Strategy For Determining Propositional Satisfiability IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple algorithm for determining the satisfiability of propositional formulas in Conjunctive Normal Form. |
Ramin Zabih; David McAllester; |
| 1987 | 1 | Intention = Choice + Commitment IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper provides a logical analysis of the concept of intention as composed of two more basic concepts, choice (or goal) and commitment. |
Philip R. Cohen; Hector J. Levesque; |
| 1987 | 2 | Reactive Reasoning And Planning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, the reasoning and planning capabilities of an autonomous mobile robot are described; The reasoning system that controls the robot is designed to exhibit the kind of behavior expected of a rational agent, and is endowed with the psychological attitudes of belief, desire, and intention. |
Michael P. Georgeff; Amy L. Lansky; |
| 1987 | 3 | An Investigation Into Reactive Planning In Complex Domains IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A model of purely reactive planning is proposed based on the concept of reactive action packages. |
R. James Firby; |
| 1987 | 4 | Pengi: An Implementation Of A Theory Of Activity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have used our dynamic theories to design a program, called Pengi, that engages in complex, apparently planful activity without requiring explicit models of the world. |
Philip E. Agre; David Chapman; |
| 1987 | 5 | Foundations Of Assumption-based Truth Maintenance Systems: Preliminary Report IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we (1) define the concept of a Clause Management System (CMS) – a generalization of de Kleer’s ATMS, (2) motivate such systems in terms of efficiency of search and abductive reasoning, <and (3) characterize the computation affected by a CMS in terms of the concept of prime implicants. |
Raymond Reiter; Johan de Kleer; |
| 1987 | 6 | Modular Learning In Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a way of coupling autoassociative learning modules into hierarchies that should greatly improve the performance of learning algorithms in large-scale systems. |
Dana H. Ballard; |
| 1987 | 7 | TREAT: A Better Match Algorithm For AI Production Systems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the TREAT match algorithm for AI production systems. |
Daniel P. Miranker; |
| 1987 | 8 | A Skeptical Theory Of Inheritance In Nonmonotonic Semantic Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a new approach to inheritance reasoning in semantic networks allowing for multiple inheritance with exceptions. |
John F. Horty; Richmond H. Thomason; David S. Touretzky; |
| 1987 | 9 | An Approach To Default Reasoning Based On A First-Order Conditional Logic IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an approach to default reasoning based on an extension to classical first-order logic. |
James P. Delgrande; |
| 1987 | 10 | On Stratified Autoepistemic Theories IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we investigate some properties of "autoepistemic logic" approach to the formalization of common sense reasoning suggested by R. Moore in [Moore, 1985]. |
Michael Gelfond; |
| 1987 | 11 | Improving Inference Through Conceptual Clustering IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents COBWEB, a conceptual clustering system that organizes data to maximize inference abilities. |
Douglas Fisher; |
| 1987 | 12 | Inference In Text Understanding IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An alternative, unified approach is proposed. |
Peter Norvig; |
| 1987 | 13 | The Logic Of Representing Dependencies By Directed Graphs IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper provides an axiomatic basis, called a semi-graphoid which captures the structure common to all four types of dependencies and explores the expressive power of DAGs in representing various types of data dependencies. |
Judea Pearl; Thomas Verma; |
| 1987 | 14 | Defining Operationality For Explanation-based Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Operationality is the key property that distinguishes the final description learned in an explanation-based system from the initial concept description input to the system. Yet … |
Richard M. Keller; |
| 1987 | 15 | Abstraction By Time-Scale In Qualitative Simulation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a method called Time-Scale Abstraction for structuring a complex system as a hierarchy of smaller, interacting equilibrium mechanisms. |
Benjamin Kuipers; |
| 1986 | 1 | The Multi-Purpose Incremental Learning System AQ15 And Its Testing Application To Three Medical Domains IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A surprising and potentially significant result is the demonstration that by applying the proposed method of cover truncation and analogical matching, called TRUNC, one may drastically decrease the complexity of the knowledge base without affecting its performance accuracy. |
Ryszard Michalski; Igor Mozetic; Jiarong Hong; Nada Lavrac; |
| 1986 | 2 | Constraint Propagation Algorithms For Temporal Reasoning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper considers computational aspects of several temporal representation languages. |
Marc Vilain; Henry Kautz; |
| 1986 | 3 | And/Or Graph Representation Of Assembly Plans IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a compact representation of all possible assembly plans of a given product using AND/OR graphs. |
Luiz Homem de Mello; A. C. Sanderson; |
| 1986 | 4 | Generalized Plan Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper outlines a new theory of plan recognition that is significantly more powerful than previous approaches. |
Henry A. Kautz; James F. Allen; |
| 1986 | 5 | CHEF: A Model Of Case-Based Planning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Case-based planning is based on the idea that a machine planner should make use of its own past experience in developing new plans, relying on its memories instead of a base of … |
Kristian J. Hammond; |
| 1986 | 6 | A Case Study Of Incremental Concept Induction IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we introduce 3 dimensions for characterizing incremental concept induction systems which relate to the cost and quality of learning. |
Jeffrey C. Schlimmer; Douglas Fisher; |
| 1986 | 7 | Default Reasoning, Nonmonotonic Logics, And The Frame Problem IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nonmonotonic formal systems have been proposed as an extension to classical first-order logic that will capture the process of human "default reasoning" or "plausible inference" through their inference mechanisms just as modus ponens provides a model for deductive reasoning. |
Steve Hanks; Drew McDermott; |
| 1986 | 8 | The Structure-Mapping Engine IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We review the Structure-Mapping theory and describe the design of the engine. |
Brian Falkenhainer; Kenneth D. Forbus; Dedre Gentner; |
| 1986 | 9 | Order Of Magnitude Reasoning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a methodology for extending representation and reasoning in Qualitative Physics. |
Olivier Raiman; |
| 1986 | 10 | Beyond Incremental Processing: Tracking Concept Drift IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a learning method that is able to learn complex Boolean characterizations while tolerating noise and drift. |
Jeffrey Schlimmer; Richard Granger; |
| 1986 | 11 | SNePS Considered As A Fully Intensional Propositional Semantic Network IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a formal syntax and semantics for SNePS considered as the (modeled) mind of a cognitive agent. |
Stuart C. Shapiro; William J. Rapaport; |
| 1986 | 12 | Cooperation Without Communication IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we examine various constraints on the actions of agents in such situations and discuss the effects of these constraints on their derived utility. |
Michael R. Genesereth; Matthew L. Ginsberg; Jeffrey S. Rosenschein; |
| 1986 | 13 | Learning While Searching In Constraint-Satisfaction-Problems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper examines another issue (much less explored) which arises in dead-ends. |
Rina Dechter; |
| 1986 | 14 | A Framework For Evidential-Reasoning Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Both the formal basis and a framework for the implementation of automated reasoning systems based upon these techniques are presented. |
John D. Lowrance; Thomas D. Garvey; Thomas M. Strat; |
| 1986 | 15 | Doing Time: Putting Qualitative Reasoning On Firmer Ground IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a general approach to behavioral prediction which overcomes many of these limitations. |
Brian C. Williams; |
| 1984 | 1 | A Logic Of Implicit And Explicit Belief IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we point out deficiencies in current semantic treatments of knowledge and belief (including recent syntactic approaches) and suggest a new analysis in the form of a logic that avoids these shortcomings and is also more viable computationally. |
Hector J. Levesque; |
| 1984 | 2 | The Tractability Of Subsumption In Frame-Based Description Languages IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present evidence as to how the cost of computing one kind of inference is directly related to the expressiveness of the representation language. |
Ronald J. Brachman; Hector J. Levesque; |
| 1984 | 3 | Classification Problem Solving IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The classification problem-solving model provides a useful framework for recognizing and representing similar problems, for designing representation tools, and for understanding why non-classification problems require different problem-solving methods. |
William J. Clancey; |
| 1984 | 4 | Path Relaxation: Path Planning For A Mobile Robot IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Path Relaxation is a method of planning safe paths around obstacles for mobile robots. It works in two steps: a global grid starch that finds a rough path, followed by a local … |
Charles E. Thorpe; |
| 1984 | 5 | Personal Construct Theory And The Transfer Of Human Expertise IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Methods of knowledge elicitation and analysis from psychotherapy based on enhancements to George Kelly’s Personal Construct Theory are applied to this process. |
John H. Boose; |
| 1984 | 6 | Maintaining Diversity In Genetic Search IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Genetic adaptive algorithms provide an efficient way to search large function spaces, and are increasingly being used in learning systems. |
Michael L. Mauldin; |
| 1984 | 7 | Shading Into Texture IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To extend such methods to real surfaces we must have a model that also applies to rough surfaces. |
Alex P. Pentland; |
| 1984 | 8 | Implicit Ordering Of Defaults In Inheritance Systems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The flaws of the shortest-path ordering become apparent when we consider multiple inheritance. |
David S. Touretzky; |
| 1984 | 9 | A Theory Of Action For MultiAgent Planning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A theory of action suitable for reasoning about events in multiagent or dynamically changing environments is presented. |
Michael Georgeff; |
| 1984 | 10 | Choices Without Backtracking IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper discusses a method of dealing with choice that does not involve any backtracking yet explores no more alternatives than the best backtracking schemes. |
Johan de Kleer; |
| 1984 | 11 | Automated Cognitive Modeling IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe an approach to automating the construction of cognitive process models. |
Pat Langley; Stellan Ohlsson; |
| 1984 | 12 | Intention-Based Diagnosis Of Programming Errors IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we will discuss the methods which PROUST uses to identify and diagnose non-syntactic bugs. |
Elliot Soloway; |
| 1984 | 13 | Living Up To Expectations: Computing Expert Responses IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper focusses on identifying and avoiding potentially misleading responses by acknowledging types of "informing behavior" usually expected of an expert. |
Aravind Joshi; Bonnie Webber; Ralph M. Weischedel; |
| 1984 | 14 | Five Parallel Algorithms For Production System Execution On The DADO Machine IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we specify five abstract algorithms for the parallel execution of production systems on the DAD0 machine. |
Salvatore J. Stolfo; |
| 1984 | 15 | Continuous Belief Functions For Evidential Reasoning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a new representation of belief for continuous variables that provides both a conceptual framework and a computationally tractable implementation within the Shafer-Dempster theory. |
Thomas M. Strat; |
| 1983 | 1 | Why AM And Eurisko Appear To Work IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: That task — learning new heuristics by discovery — turned out to be much more difficult than was realized initially, and we have just now achieved some successes at it. |
Douglas B. Lenat; John Seely Brown; |
| 1983 | 2 | Communication And Interaction In Multi-Agent Planning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method for synthesizing multi-agent plans from simpler single-agent plans is described. |
Michael Georgeff; |
| 1983 | 3 | Learning Physical Descriptions From Functional Definitions, Examples, And Precedents IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It is easier to talk about purpose and what things are for. |
Patrick H. Winston; Boris Katz; Thomas O. Binford; Michael Lowry; |
| 1983 | 4 | On Inheritance Hierarchies With Exceptions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using default logic, we formalize NETL-like inheritance hierar-chies with exceptions. |
David W. Etherington; Raymond Reiter; |
| 1983 | 5 | An Overview Of The Penman Text Generation System IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The problem of programming computers to produce natural language explanations and other texts on demand is an active research area in artificial intelligence. In the past, … |
William C. Mann; |
| 1983 | 6 | Derivational Analogy And Its Role In Problem Solving IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The derivational analogy approach is advocated as a means of implementing reasoning from individual cases in expert systems.’ |
Jaime G. Carbonell; |
| 1983 | 7 | An Overview Of Meta-Level Architecture IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the language, describes an appropriate, and cliscusses the issues of compiling. |
Michael R. Genesereth; |
| 1983 | 8 | Diagnosis Via Causal Reasoning: Paths Of Interaction And The Locality Principle IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In developing such a system for troubleshooting digital electronics, we have argued for the importance of pathways of causal interaction as a key concept. |
Randall Davis; |
| 1983 | 9 | The Bayesian Basis Of Common Sense Medical Diagnosis IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the paper, we show that the objections most frequently related against the use of Bayesian statistics within the AI-in-Medicine community do not seem to hold. |
Eugene Charniak; |
| 1983 | 10 | Tracking User Goals In An Information-Seeking Environment IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a model for hypothesizing and tracking the changing task-level goals of a speaker during the course of an information-seeking dialogue. |
Sandra Carberry; |
| 1983 | 11 | The Advantages Of Abstract Control Knowledge In Expert System Design IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A poorly designed knowledge base can be as cryptic as an arbitrary program and just as difficult to maintain. Representing control knowledge abstractly, separately from domain … |
William J. Clancey; |
| 1983 | 12 | Schema Selection And Stochastic Inference In Modular Environments IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm is given for simulating this computation once schemas encoding the modules of the environ-ment have been selected. |
Paul Smolensky; |
| 1983 | 13 | A Variational Approach To Edge Detection IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes an attempt to formulate set of edge detection criteria that capture as directly as possible the desirable properties of the detector. |
John Canny; |
| 1983 | 14 | Human Procedural Skill Acquisition: Theory, Model And Psychological Validation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The method used with this theory is presented. |
Kurt VanLehn; |
| 1983 | 15 | KRYPTON: Integrating Terminology And Assertion IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have attempted to overcome these limitations in a new, hybrid knowledge representation system, called "KRYPTON". |
Ronald J. Brachman; Hector J. Levesque; Richard E. Fikes; |
| 1982 | 1 | Reverend Bayes On Inference Engines: A Distributed Hierarchical Approach IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents generalizations of Bayes likelihood-ratio updating rule which facilitate an asynchronous propagation of the impacts of new beliefs and/or new evidence in hierarchically organized inference structures with multi-hypotheses variables. |
Judea Pearl; |
| 1982 | 2 | Solving The Find-Path Problem By Good Representation Of Free Space IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An algorithm is presented which efficiently finds good collision free paths for convex polygonal bodies through space Iittered with obstacle polygons. |
Rodney A. Brooks; |
| 1982 | 3 | Talking To UNIX In English: An Overview Of UC IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: UC (UNIX Consultant) is an intelligent natural language interface that allows naive users to communicate with the UNIX** operating system in ordinary English. UC is currently … |
Robert Wilensky; |
| 1982 | 4 | The Role Of Logic In Knowledge Representation And Commonsense Reasoning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We take issue with the commonly held view (as expressed by Newell [1980]) that the use of representations based on formal logic is inappropriate in most applications of artificial intelligence. |
Robert C. Moore; |
| 1982 | 5 | A Nonclausal Connection-Graph Resolution Theorem-Proving Program IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A new theorem-proving program, combining the use of non-clausal resolution and connection graphs, is described. The use of nonclausal resolution as the inference system eliminates … |
Mark E. Stickel; |
| 1982 | 6 | Deep Versus Compiled Knowledge Approaches To Diagnostic Problem-Solving IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we argue that given a body of underlying knowledge that is relevant to diagnostic reasoning in a medical domain, it is possible to create a diagnostic structure which has all the relevant aspects of the underlying knowledge "compiled" into it in such a way that all the diagnostic problems in its scope can be solved efficiently, without, generally speaking, any need to access the underlying structures. |
B. Chandrasekaran; Sanjay Mittal; |
| 1982 | 7 | A System For Reasoning About Time IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe the salient features of a new system for reasoning about time. |
Marc B. Vilain; |
| 1982 | 8 | REACTOR: An Expert System For Diagnosis And Treatment Of Nuclear Reactor Accidents IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper covers the background of the nuclear industry and why expert system technology may prove valuable in the reactor control room. |
William R. Nelson; |
| 1982 | 9 | Diagnosis Based On Description Of Structure And Function IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe our work to date on (i) a language for describing structure, (ii) a language for describing function, and (iii) a set of principles for troubleshooting that uses the two descriptions to guide its investigation. |
RANDALL DAVIS et. al. |
| 1982 | 10 | User Participation In The Reasoning Processes Of Expert Systems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We argue that expert systems, if they are to satisfy the legitimate needs of their users, must include dialogue capabilities as sophisticated as those proposed in current Natural Language research. We present data demonstrating that user-expert dialogues are best viewed as a negotiation process, and we describe the exchanges that compose the dialogue in terms of the motivations, goals, strategies, and moves of the participants. |
Martha E. Pollack; Julia Hirschberg; Bonnie Webber; |
| 1982 | 11 | A Framework For Distributed Problem Solving IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a framework for distributed problem solving that describes some of the expertise an agent working in a multi-agent environment must have. |
Dave McArthur; Randy Steeb; Stephanie Cammarata; |
| 1982 | 12 | RABBIT: An Intelligent Database Assistant IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have designed and implemented an intelligent database assistant to aid the user in formulating a query. |
Frederich N. Tou; Michael D. Williams; Richard Fikes; Austin Henderson; Thomas Malone; |
| 1982 | 13 | Diagnosis Using Hierarchical Design Models IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new algorithm for the diagnosis of computer hardware faults. |
Michael G. Genesereth; |
| 1982 | 14 | DADO: A Tree-Structured Machine Architecture For Production Systems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes a general procedure for the parallel execution of production systems on the DADO machine, and outlines in general terms how this procedure can be extended to include commutative and multiple, independent production systems. |
Salvatore J. Stolfo; David Elliot Shaw; |
| 1982 | 15 | Tracking Known Three-Dimensional Objects IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A method of visually tracking a known three-dimensional object is described. |
Donald B. Gennery; |