Research map / Graph learning / GNN architectures
Graph Attention Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use masked attention to assign different weights to neighbors instead of GCN aggregation | GAT · Cora | accuracy: 1.5\% | Helped |
| use masked attention to assign different weights to neighbors instead of GCN aggregation | GAT · Citeseer | accuracy: 1.6\% | Helped |
| use masked attention to assign different weights to neighbors instead of GCN aggregation | GAT · Pubmed | accuracy | No clear effect |
| replace constant neighbor weights with learned attention weights (ablation) | GAT · PPI | micro-F1: 3.9\% | Helped |
| aggregate the entire neighborhood rather than use sampled neighborhoods | GAT · PPI | micro-F1: 20.5\% | Helped |
Closest papers by meaning
- Learnable Graph Convolutional Attention Networks (ICLR 2023 · similarity 0.92)
- How Attentive are Graph Attention Networks? (ICLR 2022 · similarity 0.91)
- Towards Deep Attention in Graph Neural Networks: Problems and Remedies (ICML 2023 · similarity 0.91)
- Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models (ICML 2025 · similarity 0.89)
- HONGAT: Graph Attention Networks in the Presence of High-Order Neighbors (AAAI 2024 · similarity 0.89)
- Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.