{"url":"/method/gat","slug":"gat","name":"GAT","full_name":"Graph Attention Network","full_name_withheld":false,"description_markdown":"A **Graph Attention Network (GAT)** is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods’ features, a GAT enables (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront.\r\n\r\nSee [here](https://docs.dgl.ai/en/0.4.x/tutorials/models/1_gnn/9_gat.html) for an explanation by DGL.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Graph Attention Networks","paper":"/paper/graph-attention-networks","first_author":"Petar Veličković","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/graph-attention-networks"},"source":{"url":"http://arxiv.org/abs/1710.10903v3","title":"Graph Attention Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]}],"n_papers_tagged":197,"archive_num_papers":197,"papers_newest_first":[{"paper":null,"title":"Temporal-Aware Graph Attention Network for Cryptocurrency Transaction Fraud Detection","date":"2025-06-26","arxiv_id":"2506.21382","n_code_links":0,"syntology":null},{"paper":null,"title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","date":"2025-06-17","arxiv_id":"2506.14114","n_code_links":0,"syntology":null},{"paper":null,"title":"Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies","date":"2025-06-01","arxiv_id":"2506.00770","n_code_links":0,"syntology":null},{"paper":"/paper/2505-10711","title":"GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics","date":"2025-05-15","arxiv_id":"2505.10711","n_code_links":1,"syntology":null},{"paper":null,"title":"Event-Triggered GAT-LSTM Framework for Attack Detection in Heating, Ventilation, and Air Conditioning Systems","date":"2025-05-06","arxiv_id":"2505.03559","n_code_links":0,"syntology":null},{"paper":null,"title":"Robustness questions the interpretability of graph neural networks: what to do?","date":"2025-05-05","arxiv_id":"2505.02566","n_code_links":0,"syntology":null},{"paper":null,"title":"Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention","date":"2025-04-11","arxiv_id":"2504.08183","n_code_links":0,"syntology":null},{"paper":null,"title":"Dynamic Power Flow Analysis and Fault Characteristics: A Graph Attention Neural Network","date":"2025-03-19","arxiv_id":"2503.15563","n_code_links":0,"syntology":null},{"paper":null,"title":"Lyapunov-Based Graph Neural Networks for Adaptive Control of Multi-Agent Systems","date":"2025-03-19","arxiv_id":"2503.15360","n_code_links":0,"syntology":null},{"paper":null,"title":"Fault Localization and State Estimation of Power Grid under Parallel Cyber-Physical Attacks","date":"2025-03-03","arxiv_id":"2503.05797","n_code_links":0,"syntology":null},{"paper":null,"title":"Feature-based Graph Attention Networks Improve Online Continual Learning","date":"2025-02-13","arxiv_id":"2502.09143","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-traffic-state-and-trajectory-for","title":"Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning","date":"2025-02-08","arxiv_id":"2502.06870","n_code_links":1,"syntology":null},{"paper":null,"title":"Graph Neural Network Enabled Pinching Antennas","date":"2025-02-08","arxiv_id":"2502.05447","n_code_links":0,"syntology":null},{"paper":"/paper/graph-neural-networks-for-efficient-ac-power","title":"Graph Neural Networks for Efficient AC Power Flow Prediction in Power Grids","date":"2025-02-08","arxiv_id":"2502.05702","n_code_links":1,"syntology":null},{"paper":"/paper/generative-autoregressive-transformers-for","title":"Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction","date":"2025-02-06","arxiv_id":"2502.04521","n_code_links":1,"syntology":null},{"paper":"/paper/graph-machine-learning-for-flight-delay","title":"Graph machine learning for flight delay prediction due to holding manouver","date":"2025-02-06","arxiv_id":"2502.04233","n_code_links":1,"syntology":null},{"paper":null,"title":"Utilizing Graph Neural Networks for Effective Link Prediction in Microservice Architectures","date":"2025-01-25","arxiv_id":"2501.15019","n_code_links":0,"syntology":null},{"paper":"/paper/an-attentive-graph-agent-for-topology","title":"An Attentive Graph Agent for Topology-Adaptive Cyber Defence","date":"2025-01-24","arxiv_id":"2501.14700","n_code_links":1,"syntology":null},{"paper":null,"title":"Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models","date":"2025-01-20","arxiv_id":"2501.11247","n_code_links":0,"syntology":null},{"paper":null,"title":"Detection, Retrieval, and Explanation Unified: A Violence Detection System Based on Knowledge Graphs and GAT","date":"2025-01-07","arxiv_id":"2501.06224","n_code_links":0,"syntology":null},{"paper":"/paper/dual-level-adaptive-incongruity-enhanced","title":"Dual-level Adaptive Incongruity-enhanced Model for Multimodal Sarcasm Detection","date":"2025-01-07","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"GAIS: A Novel Approach to Instance Selection with Graph Attention Networks","date":"2024-12-26","arxiv_id":"2412.19201","n_code_links":0,"syntology":null},{"paper":"/paper/lase-learned-adjacency-spectral-embeddings","title":"LASE: Learned Adjacency Spectral Embeddings","date":"2024-12-23","arxiv_id":"2412.17734","n_code_links":1,"syntology":null},{"paper":null,"title":"FedGAT: A Privacy-Preserving Federated Approximation Algorithm for Graph Attention Networks","date":"2024-12-20","arxiv_id":"2412.16144","n_code_links":0,"syntology":null},{"paper":null,"title":"Training Graph Neural Networks Using Non-Robust Samples","date":"2024-12-19","arxiv_id":"2412.14738","n_code_links":0,"syntology":null},{"paper":null,"title":"Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks","date":"2024-12-11","arxiv_id":"2412.08555","n_code_links":0,"syntology":null},{"paper":null,"title":"CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation","date":"2024-12-01","arxiv_id":"2412.00749","n_code_links":0,"syntology":null},{"paper":"/paper/locate-gat-modeling-multi-scale-local-context","title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","date":"2024-11-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/df-gnn-dynamic-fusion-framework-for-attention","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","date":"2024-11-25","arxiv_id":"2411.16127","n_code_links":1,"syntology":null},{"paper":"/paper/graph-neural-networks-in-supply-chain","title":"Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks","date":"2024-11-13","arxiv_id":"2411.08550","n_code_links":3,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/graph-attention","name":"Graph Attention","papers":102},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":43},{"task":"/task/node-classification","name":"Node Classification","papers":35},{"task":"/task/link-prediction","name":"Link Prediction","papers":11},{"task":"/task/graph-learning","name":"Graph Learning","papers":9},{"task":"/task/representation-learning","name":"Representation Learning","papers":9},{"task":"/task/graph-classification","name":"Graph Classification","papers":8},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":7},{"task":"/task/prediction","name":"Prediction","papers":7},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":6},{"task":"/task/benchmarking","name":"Benchmarking","papers":6},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":6},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":5},{"task":"/task/classification-1","name":"Classification","papers":5},{"task":"/task/classification","name":"General Classification","papers":5},{"task":"/task/management","name":"Management","papers":5},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":5},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":5},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4}],"tasks_shown":20,"n_tasks":193,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":3},{"year":"2019","papers":9},{"year":"2020","papers":26},{"year":"2021","papers":33},{"year":"2022","papers":28},{"year":"2023","papers":36},{"year":"2024","papers":40},{"year":"2025","papers":21}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gat"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}