Methods › Graphs › Graph Models › GAT

Graph Attention Network

GAT

197 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Graph Attention102
Graph Neural Network43
Node Classification35
Link Prediction11
Graph Learning9
Representation Learning9
Graph Classification8
Knowledge Graphs7
Prediction7
Anomaly Detection6
Benchmarking6
Graph Representation Learning6
Adversarial Robustness5
Classification5
General Classification5
Management5
Recommendation Systems5
Reinforcement Learning (RL)5
Computational Efficiency4
Data Augmentation4

Usage over time archive 2025-07-28

Papers per year tagged with GAT: 2017 to 2025, peak 40 40 0 2017: 1 paper 2017 2018: 3 papers 2018 2019: 9 papers 2019 2020: 26 papers 2020 2021: 33 papers 2021 2022: 28 papers 2022 2023: 36 papers 2023 2024: 40 papers 2024 2025: 21 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (197 dated). Bars are counts, not a trend claim.

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

Graph Models

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