Research map / Graph learning / GNN architectures
Edge Representation Learning with Hypergraphs
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 |
|---|---|---|---|
| pool by dropping edges via dual hypergraph (HyperDrop) instead of node-based hierarchical pooling | GCN graph classifier · 10 graph classification datasets | average score: 68.49 -> 73.20 | Helped |
| combine HyperDrop with global pooling GMT | GMT · 10 graph classification datasets | average score: 73.07 -> 73.57 | Helped |
| combine HyperDrop with GMT | HyperDrop · MUTAG | accuracy: 84.00 -> 85.72 | Helped |
| HyperDrop vs GMT on ToxCast | GMT · ToxCast | ROC-AUC: 65.44 -> 64.21 | Hurt |
| add explicit edge representations from EHGNN (ablation) | HyperDrop · graph classification ablation | accuracy | Helped |
| use learned HyperDrop instead of random edge drop (ablation) | EHGNN · graph classification ablation | accuracy | Helped |
| use HyperDrop instead of HyperCluster for classification (ablation) | EHGNN · graph classification ablation | accuracy | Helped |
| use EHGNN with HyperDrop as depth increases | deep GCN · node classification (over-smoothing) | accuracy | Helped |
| use EHGNN edge representations in generator encoder | MolGAN · molecule generation | SA/QED scores | Helped |
| use EHGNN explicit edge representations | MARS · molecule generation | success rate | Helped |
Closest papers by meaning
- Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion (AAAI 2024 · similarity 0.90)
- Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating (AAAI 2023 · similarity 0.90)
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (ICML 2024 · similarity 0.88)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.88)
- Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.87)
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.87)
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.