Methods › Graphs › Graph Models › GAT
Graph Attention Network
GAT
Introduced by Petar Veličković et al. in Graph Attention Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 archive 2025-07-28
30 shown of 197, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Temporal-Aware Graph Attention Network for Cryptocurrency Transaction Fraud Detection 26 Jun 2025 · 0 repositories · arXiv:2506.21382
-
Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization 17 Jun 2025 · 0 repositories · arXiv:2506.14114
-
Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies 1 Jun 2025 · 0 repositories · arXiv:2506.00770
-
GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics 15 May 2025 · 1 repository · arXiv:2505.10711
-
Event-Triggered GAT-LSTM Framework for Attack Detection in Heating, Ventilation, and Air Conditioning Systems 6 May 2025 · 0 repositories · arXiv:2505.03559
-
Robustness questions the interpretability of graph neural networks: what to do? 5 May 2025 · 0 repositories · arXiv:2505.02566
-
Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention 11 Apr 2025 · 0 repositories · arXiv:2504.08183
-
Dynamic Power Flow Analysis and Fault Characteristics: A Graph Attention Neural Network 19 Mar 2025 · 0 repositories · arXiv:2503.15563
-
Lyapunov-Based Graph Neural Networks for Adaptive Control of Multi-Agent Systems 19 Mar 2025 · 0 repositories · arXiv:2503.15360
-
Fault Localization and State Estimation of Power Grid under Parallel Cyber-Physical Attacks 3 Mar 2025 · 0 repositories · arXiv:2503.05797
-
Feature-based Graph Attention Networks Improve Online Continual Learning 13 Feb 2025 · 0 repositories · arXiv:2502.09143
-
Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning 8 Feb 2025 · 1 repository · arXiv:2502.06870
-
Graph Neural Network Enabled Pinching Antennas 8 Feb 2025 · 0 repositories · arXiv:2502.05447
-
Graph Neural Networks for Efficient AC Power Flow Prediction in Power Grids 8 Feb 2025 · 1 repository · arXiv:2502.05702
-
Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction 6 Feb 2025 · 1 repository · arXiv:2502.04521
-
Graph machine learning for flight delay prediction due to holding manouver 6 Feb 2025 · 1 repository · arXiv:2502.04233
-
Utilizing Graph Neural Networks for Effective Link Prediction in Microservice Architectures 25 Jan 2025 · 0 repositories · arXiv:2501.15019
-
An Attentive Graph Agent for Topology-Adaptive Cyber Defence 24 Jan 2025 · 1 repository · arXiv:2501.14700
-
Multivariate Wireless Link Quality Prediction Based on Pre-trained Large Language Models 20 Jan 2025 · 0 repositories · arXiv:2501.11247
-
Detection, Retrieval, and Explanation Unified: A Violence Detection System Based on Knowledge Graphs and GAT 7 Jan 2025 · 0 repositories · arXiv:2501.06224
-
Dual-level Adaptive Incongruity-enhanced Model for Multimodal Sarcasm Detection 7 Jan 2025 · 1 repository
-
GAIS: A Novel Approach to Instance Selection with Graph Attention Networks 26 Dec 2024 · 0 repositories · arXiv:2412.19201
-
LASE: Learned Adjacency Spectral Embeddings 23 Dec 2024 · 1 repository · arXiv:2412.17734
-
FedGAT: A Privacy-Preserving Federated Approximation Algorithm for Graph Attention Networks 20 Dec 2024 · 0 repositories · arXiv:2412.16144
-
Training Graph Neural Networks Using Non-Robust Samples 19 Dec 2024 · 0 repositories · arXiv:2412.14738
-
Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks 11 Dec 2024 · 0 repositories · arXiv:2412.08555
-
CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation 1 Dec 2024 · 0 repositories · arXiv:2412.00749
-
LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition 27 Nov 2024 · 1 repository
-
DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs 25 Nov 2024 · 1 repository · arXiv:2411.16127
-
Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks 13 Nov 2024 · 3 repositories · arXiv:2411.08550
Tasks archive 2025-07-28
20 shown of 193 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections