Research map / Graph learning / GNN architectures
Hypergraph Isomorphism Computation
Yifan Feng, Jiashu Han, Shihui Ying, Yue Gao
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 |
|---|---|---|---|
| hypergraph WL subtree kernel instead of graph WL subtree (clique expansion) | Hypergraph WL Subtree · RHG-10 | accuracy: 0.6720 -> 0.9610 | Improved |
| hypergraph WL subtree kernel instead of graph WL subtree | Hypergraph WL Subtree · RHG-Pyramid | accuracy: 0.4940 -> 0.9540 | Improved |
| hypergraph WL subtree kernel instead of graph WL subtree on graph data | Hypergraph WL Subtree · IMDB-BINARY | accuracy: 0.7440 -> 0.7440 | No clear effect |
| hypergraph WL subtree kernel instead of graph WL subtree on graph data | Hypergraph WL Subtree · NCI1 | accuracy: 0.7487 -> 0.7487 | No clear effect |
| hyperedge kernel instead of subtree kernel (ablation) | Hypergraph WL Hyperedge · RHG-10 | accuracy: 0.9610 -> 0.9030 | Hurt |
| hyperedge kernel instead of subtree kernel (ablation) | Hypergraph WL Hyperedge · RG-Sub | accuracy: 0.9190 -> 0.9250 | Improved |
| hyperedge kernel instead of subtree kernel (ablation) | Hypergraph WL Hyperedge · NCI1 | accuracy: 0.7487 -> 0.7037 | Hurt |
| hyperedge kernel instead of subtree kernel on IMDB-Wri datasets (ablation) | Hypergraph WL Hyperedge · IMDB-Wri-Form/Genre | accuracy | Improved |
| hypergraph WL subtree instead of hypergraph directed line kernel | Hypergraph WL Subtree · RHG-Pyramid | accuracy: 0.9410 -> 0.9540 | Improved |
| hypergraph WL subtree instead of hypergraph rooted (sampling) kernel | Hypergraph WL Subtree · RHG-10 | accuracy: 0.5545 -> 0.9610 | Improved |
Closest papers by meaning
- Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms (ICML 2025 · similarity 0.90)
- Beyond Graphs: Can Large Language Models Comprehend Hypergraphs? (ICLR 2025 · similarity 0.89)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.87)
- Hypergraph Joint Representation Learning for Hypervertices and Hyperedges via Cross Expansion (AAAI 2024 · similarity 0.86)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.86)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.86)
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.
