Graph Attention Networks

Also known as GAT

Ask about this topic

Overview

Graph Attention Networks study how neural models can use a graph’s connections while learning which neighboring nodes matter most for a task. Methods such as GAT and GATv2 use attention over neighbors, with extensions for edge features, multiple relations, time-varying graphs, and hierarchical or sparse aggregation. They are applied to node classification, link prediction, recommendation, forecasting, and scientific or medical data, with evaluations ranging from standard graph benchmarks to traffic, molecular, and brain-connectivity datasets. A central tension is that adaptive attention can capture useful context and improve explanations, but its gains are not universal, and scaling, noisy or incomplete graph structure, and comparisons with simpler message-passing methods remain important challenges.

Latest papers

CardsList

75 papers6 papers in the last four weeks, up 20% on the four weeks before. 0.0% of all new papers.

  1. NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation

    Mar 20, 2026Quang Dang Huynh, Xuefei Yin, Andrew Busch +4Human Pose EstimationSpatiotemporal GNNs

    Griffith University

  2. GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection

    Mar 16, 2026Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou +1Few-Shot Anomaly DetectionIndustrial Anomaly Detection

    Harokopio University of Athens, Athens, Greece · National and Kapodistrian University of Athens, Athens, Greece · Archimedes, Athena Research Center, Athens, Greece +1

  3. Gated Graph Attention Networks for Predicting Duration of Large Scale Power Outages Induced by Natural Disasters

    Mar 14, 2026Chenghao Duan, Chuanyi Ji, Anwar Walid +1Power SystemsGraph Attention Networks

    School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA · Department of Electrical Engineering, Columbia University, New York, NY, USA · School of Business, University of California, Riverside, Riverside, CA, USA

  4. Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks

    Mar 11, 2026Mohamad Alkadamani, Amir Ghasemi, Halim YanikomerogluHierarchical GNNsWireless Communications

    Communications Research Centre Canada, Ottawa, ON, Canada · Carleton University, Ottawa, ON, Canada

  5. A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks

    Mar 10, 2026Mohamad Alkadamani, Halim Yanikomeroglu, Amir GhasemiWireless CommunicationsGraph Attention Networks

    Department of Data Science, Communications Research Centre Canada · Department of Systems and Computer Engineering, Carleton University

  6. mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud

    Mar 9, 2026Abdullah Al Masud, Shi Xintong, Mondher Bouazizi +1Human Pose Estimation3D Human Pose Estimation

    Graduate School of Science and Technology, Keio University, Kanagawa, 223-8522, Japan · Faculty of Science and Technology, Keio University, Kanagawa, 223-8522, Japan

  7. Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning Method

    Mar 9, 2026Jing Zhang, Ke Huang, Yao Zhang +2Dynamic Graph LearningAnomaly Detection

    School of Computer Science and Technology, Xi’an University of Science and Technology, Xi’an 710600, China · School of Computer Science, Northwestern Polytechnical University, Xi’an 710021, China · Harbin Engineering University, Harbin, Heilongjiang, China, and also with the School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China

  8. Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks

    Mar 3, 2026Syeda Hareem Madani, Noureen Bibi, Adam Rafiq Jeraj +3Autism Spectrum DisorderNeuroimaging

    Salim Habib University · VentureDive · National University of Computer and Emerging Sciences

  9. PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow with Continual Learning

    Feb 24, 2026Chidozie Ezeakunne, Jose E. Tabarez, Reeju Pokharel +1Physics-Informed GNNsPower Systems

    Los Alamos National Laboratory, Los Alamos, NM, USA · Department of Physics, University of Central Florida, Orlando, FL 32816 USA

  10. A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification

    Feb 19, 2026Jingqi Lu, Keqi Han, Yun Wang +2ClassificationNode Classification

    Department of Computer Science, Emory University, USA · Department of Biomedical Informatics, Emory University, USA · College of AI, Tsinghua University, China

  11. MRC-GAT: A Meta-Relational Copula-Based Graph Attention Network for Interpretable Multimodal Alzheimer's Disease Diagnosis

    Feb 17, 2026Fatemeh Khalvandi, Saadat Izadi, Abdolah ChalechaleAlzheimer's Disease ClassificationGraph Attention Networks

    Computer Engineering Department, Razi University, Kermanshah, Iran

  12. Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability

    Feb 13, 2026Ayse Tursucular, Ayush Mohanty, Nazal Mohamed +1Federated LearningNonlinear System Identification

    Georgia Institute of Technology Atlanta, GA, USA

  13. Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

    Oct 23, 2025Fiza Husain, Anson Bastos, Anjaly Parayil +4Graph Attention NetworksHeterogeneous GNNs

    Microsoft

  14. AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs

    Sep 29, 2025Hakan Emre Gedik, Andrew Martin, Mustafa Munir +4Graph Attention NetworksCross-Attention

    The University of Texas at Austin

  15. Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator

    Sep 26, 2025Changhun Kim, Timon Conrad, Redwanul Karim +6Efficient Neural Network InferenceGraph Attention Networks

    Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · Institute of Electrical Energy Systems, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany