Research map / Graph learning / Graph self-supervised learning
Hyperbolic Kernel Graph Neural Networks for Neurocognitive Decline Analysis From Multimodal Brain Imaging
Meimei Yang, Yongheng Sun, Qianqian Wang, Andrea Bozoki, Maureen Pearl Kohi, Mingxia Liu
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 hyperbolic kernel GAT backbone instead of hyperbolic kernel GCN backbone | HKGF · ADNI SMC vs CN | AUC (%): 76.22 -> 80.42 | Improved |
| use hyperbolic kernel GAT backbone instead of hyperbolic kernel GCN backbone | HKGF · HAND ANI vs CN | AUC (%): 68.83 -> 69.74 | Mixed |
| replace Euclidean GCN-EF with hyperbolic kernel GCN fusion | GCN · ADNI SMC vs CN | AUC (%): 74.72 -> 76.22 | Improved |
| replace Euclidean GAT-LF with hyperbolic kernel GAT fusion | GAT · ADNI SMC vs CN | AUC (%): 77.67 -> 80.42 | Improved |
| replace HGCN-EF with hyperbolic kernel GCN fusion | HGCN · ADNI SMC vs CN | AUC (%): 71.10 -> 76.22 | Improved |
| replace Euclidean GCN-EF with hyperbolic kernel GCN fusion | GCN · HAND ANI vs CN | AUC (%): 65.24 -> 68.83 | Improved |
| replace HGCN-EF with hyperbolic kernel GAT fusion | HGCN · HAND ANI vs CN | AUC (%): 64.08 -> 69.74 | Improved |
| replace GAT-LF with hyperbolic kernel GAT fusion | GAT · HAND ANI vs CN | AUC (%): 62.61 -> 69.74 | Improved |
| replace GIN-EF with hyperbolic kernel GAT fusion | GIN · HAND ANI vs CN | ACC (%): 65.12 -> 71.86 | Improved |
| compare GAT-LF against HKGF1 hyperbolic kernel GCN | GAT-LF · ADNI SMC vs CN | AUC (%): 77.67 -> 76.22 | Hurt |
Closest papers by meaning
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics (NeurIPS 2023 · similarity 0.89)
- Data-Driven Network Neuroscience: On Data Collection and Benchmark (NeurIPS 2023 · similarity 0.88)
- NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders (ICML 2025 · similarity 0.85)
- Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens (NeurIPS 2025 · similarity 0.85)
- BrainOOD: Out-of-distribution Generalizable Brain Network Analysis (ICLR 2025 · similarity 0.85)
- Long-range Brain Graph Transformer (NeurIPS 2024 · similarity 0.85)
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.
