Research map / Graph learning / Graph self-supervised learning
Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
Jaeyoon Sim, Soojin Hwang, Seunghun Baek, Guorong Wu, Won Hwa Kim
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 |
|---|---|---|---|
| add adaptive multi-scale feature filtering (MSF) (ablation) | MuHL · ADNI | accuracy: 90.0 -> 93.2 | Improved |
| add hypergraph structure learning (HSL) (ablation) | MuHL · ADNI | accuracy: 76.8 -> 93.2 | Improved |
| add multi-scale transformer (MST) (ablation) | MuHL · ADNI | accuracy: 86.9 -> 93.2 | Improved |
| add adaptive multi-scale feature filtering (MSF) (ablation) | MuHL · PPMI | accuracy: 72.9 -> 76.8 | Improved |
| add hypergraph structure learning (HSL) (ablation) | MuHL · PPMI | accuracy: 67.4 -> 76.8 | Improved |
| add multi-scale transformer (MST) (ablation) | MuHL · PPMI | accuracy: 64.1 -> 76.8 | Improved |
| replace best baseline ALTER with MuHL | ALTER · ADNI | accuracy: 90.8 -> 93.2 | Improved |
| replace best baseline GAT with MuHL | GAT · PPMI | accuracy: 72.9 -> 76.8 | Improved |
| use MuHL for zero-shot transfer from ADNI-2 to ADNI-1/3/GO | dwHGCN · ADNI-2 to ADNI-1/3/GO | accuracy: 52.8 -> 56.0 | Improved |
| use MuHL for zero-shot transfer PPMI to TaoWu | BQN · PPMI to TaoWu | accuracy: 57.0 -> 60.5 | Improved |
| increase number of hyperedges M beyond 16-20 (ablation) | MuHL · ADNI | accuracy: increased up to 16 but declined beyond 20 | Hurt |
| increase hyperedge embedding dimension d_h beyond 16 (ablation) | MuHL · ADNI | accuracy: improved up to 16 then plateaued | No clear effect |
Closest papers by meaning
- HyperDiag: Temporal–Regional Hypergraph Learning via Topology-Enhanced State Propagation for Brain Disease Diagnosis (AAAI 2026 · similarity 0.90)
- Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis (NeurIPS 2026 · similarity 0.89)
- Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization (ICML 2024 · similarity 0.87)
- Learning High-Order Relationships of Brain Regions (ICML 2024 · similarity 0.86)
- Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints (NeurIPS 2025 · similarity 0.86)
- Long-range Brain Graph Transformer (NeurIPS 2024 · 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.
