Research map / Graph learning / GNN architectures
MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural Networks
Shuyang Fang, Yuqin Huang, Zelong Yang, Yintao Cai, Xiaoping Min
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 |
|---|---|---|---|
| use MC-HNN instead of FrameHGNN on featureless heterophilic Senate | MC-HNN · Senate | accuracy: 67.61 -> 78.31 | Improved |
| use MC-HNN instead of FrameHGNN | MC-HNN · House | accuracy: 72.82 -> 77.59 | Improved |
| use MC-HNN instead of FrameHGNN | MC-HNN · CiteSeer | accuracy: 74.72 -> 74.48 | No clear effect |
| use MC-HNN instead of Natural-HNN | MC-HNN · ModelNet40 | accuracy: 98.56 -> 98.52 | No clear effect |
| add multi-channel message passing (ablation) | MC-HNN · Cora | accuracy: 78.73 -> 82.33 | Improved |
| add multi-channel message passing (ablation) | MC-HNN · NTU2012 | accuracy: 90.36 -> 90.82 | No clear effect |
| add latent hyperedge type encoding (ablation) | MC-HNN · Senate | accuracy: 76.62 -> 78.31 | Improved |
| add dynamic channel gating (ablation) | MC-HNN · Cora | accuracy: 82.02 -> 82.33 | Improved |
| add channel orthogonality regularization (ablation) | MC-HNN · appendix | accuracy | No clear effect |
| add MC-HNN multi-channel design to deep models (2 to 64 layers) | MC-HNN · Cora, House, Cora-CA | accuracy vs depth | Improved |
Closest papers by meaning
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.91)
- High-Pass Matters: Theoretical Insights and Sheaflet-Based Design for Hypergraph Neural Networks (AAAI 2026 · similarity 0.91)
- LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference (ICLR 2024 · similarity 0.90)
- K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach (AAAI 2025 · similarity 0.90)
- Hypergraph Neural Architecture Search (AAAI 2024 · similarity 0.89)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.89)
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.
