Research map / Graph learning / GNN architectures
Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning
Shiyu Chen, Cencheng Shen, Youngser Park, Carey E. Priebe
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| initialize GNN with GEE embeddings instead of random features | GNN · Cora (clustering) | ARI: 0.111 -> 0.166 | Improved |
| initialize GNN with GEE embeddings instead of random features | GNN · LastFM (clustering) | ARI: 0.274 -> 0.409 | Improved |
| initialize GNN with GEE embeddings instead of random features | GNN · Email (clustering) | ARI: 0.340 -> 0.537 | Improved |
| initialize GNN with GEE embeddings instead of random features | GNN · KarateClub (clustering) | ARI: 0.725 -> 0.726 | No clear effect |
| initialize GNN with GEE embeddings instead of random features | GNN · LastFM (clustering) | Running time (s): 779.6 -> 474.1 | Improved |
| initialize GNN with GEE embeddings instead of random features | GNN · Cora (clustering) | Running time (s): 80.6 -> 59.2 | Improved |
| initialize GNN with GEE embeddings instead of random features | GNN · UAT (clustering) | Running time (s): 12.0 -> 12.4 | No clear effect |
| add GNN refinement to GEE (GG vs GEE) | GEE · Cora (clustering) | ARI: 0.137 -> 0.166 | Improved |
| initialize GNN with GEE embeddings | GNN · Cora (classification, 5% labels) | Accuracy: 0.318 -> 0.393 | Improved |
| concatenate GEE and GG embeddings (GG-C vs GG) | GG · Cora (classification, 5% labels) | Accuracy: 0.393 -> 0.426 | Improved |
| concatenate GEE and GG embeddings (GG-C vs GG) | GG · Wiki (classification, 5% labels) | Accuracy: 0.326 -> 0.304 | Hurt |
| concatenate GEE and GG embeddings (GG-C vs GEE) | GEE · ACM (classification, 5% labels) | Accuracy: 0.469 -> 0.534 | Improved |
Closest papers by meaning
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 2025 · similarity 0.91)
- Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification (NeurIPS 2024 · similarity 0.91)
- Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under Heterophily (AAAI 2025 · similarity 0.90)
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.90)
- GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights (NeurIPS 2025 · similarity 0.90)
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.
