TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/GAT

GAT

Graph Attention Network

GraphsIntroduced 2000197 papers
Source Paper

Description

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.

See here for an explanation by DGL.

Papers Using This Method

Temporal-Aware Graph Attention Network for Cryptocurrency Transaction Fraud Detection2025-06-26Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization2025-06-17Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies2025-06-01GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics2025-05-15Event-Triggered GAT-LSTM Framework for Attack Detection in Heating, Ventilation, and Air Conditioning Systems2025-05-06Robustness questions the interpretability of graph neural networks: what to do?2025-05-05Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention2025-04-11Dynamic Power Flow Analysis and Fault Characteristics: A Graph Attention Neural Network2025-03-19Lyapunov-Based Graph Neural Networks for Adaptive Control of Multi-Agent Systems2025-03-19Fault Localization and State Estimation of Power Grid under Parallel Cyber-Physical Attacks2025-03-03Feature-based Graph Attention Networks Improve Online Continual Learning2025-02-13Graph Neural Networks for Efficient AC Power Flow Prediction in Power Grids2025-02-08Graph Neural Network Enabled Pinching Antennas2025-02-08Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning2025-02-08Graph machine learning for flight delay prediction due to holding manouver2025-02-06Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction2025-02-06Utilizing Graph Neural Networks for Effective Link Prediction in Microservice Architectures2025-01-25An Attentive Graph Agent for Topology-Adaptive Cyber Defence2025-01-24Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models2025-01-20Dual-level Adaptive Incongruity-enhanced Model for Multimodal Sarcasm Detection2025-01-07