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

In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.

From the lookup's note on this name: Nothing resolved to this name, but 6 entries in Syntology's graph carry it; the most cited is “Guided Adversarial Training (GAT)”, a method in the paper “Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses” (arXiv:2011.14969, 121 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:2011.14969: its page on this site · ask the lookup about it.

Near matches the lookup lists, each a different name: HR-GAT; HR-GAT; CT-GAT; HIA-GAT; HSO-GAT; MRC-GAT; GAT-MDN; GAT-NeRF.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 197 · with a code link: 90 · where Syntology ran a sample: 24 (21 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (24 of 197 tagged: 21 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 197, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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