Research map / Graph learning / Graph algorithms and clustering
Watch Your Step: Learning Node Embeddings via Graph Attention
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 |
|---|---|---|---|
| Replace a fixed context distribution with learned softmax attention over transition-matrix powers | Graph embedding · wiki-vote, dim 64 | ROC-AUC: 91.7 -> 93.8 ± 0.13 | Helped |
| Replace a fixed context distribution with learned softmax attention over transition-matrix powers | Graph embedding · ego-Facebook, dim 64 | ROC-AUC: 99.1 -> 99.4 ± 0.10 | Helped |
| Replace a fixed context distribution with learned softmax attention over transition-matrix powers | Graph embedding · ca-AstroPh, dim 128 | ROC-AUC: 97.7 -> 98.1 ± 0.49 | Helped |
| Replace a fixed context distribution with learned softmax attention over transition-matrix powers | Graph embedding · ca-HepTh, dim 64 | ROC-AUC: 91.8 -> 93.6 ± 0.06 | Helped |
| Replace a fixed context distribution with learned softmax attention over transition-matrix powers | Graph embedding · PPI, dim 128 | ROC-AUC: 83.9 -> 91.0 ± 0.28 | Helped |
| Vary maximum context length C and attention regularization β (ablation) | Graph Attention · Link prediction datasets | accuracy metrics: 1% to 2% | No clear effect |
Closest papers by meaning
- Fisher Information Embedding for Node and Graph Learning (ICML 2023 · similarity 0.93)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.88)
- Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning (ICLR 2025 · similarity 0.88)
- A Topological Perspective on Demystifying GNN-Based Link Prediction Performance (ICLR 2024 · similarity 0.88)
- VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections (ICLR 2024 · similarity 0.88)
- Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models (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.