Research map / Graph learning / Knowledge and temporal graphs
NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
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 |
|---|---|---|---|
| use correlation matrix as node features instead of BOLD signals (ablation) | 10 GNNs · HCP-Gender (100/400/1000 ROIs) | accuracy: 48.15 -> 78.80 | Helped |
| combine BOLD signals with correlation features (ablation) | GNNs · HCP-Gender | accuracy: 78.80 -> 51.30 | Hurt |
| increase number of ROIs from 100 to 1000 (ablation) | GNNs with correlation features · HCP-Gender | average accuracy: 67.30 -> 72.98 | Helped |
| sparsify graph (sparse vs medium) at 1000 ROIs (ablation) | GNNs · HCP-Gender | accuracy: 78.80 -> 82.13 | Mixed |
| use dense instead of sparse graph for k-GNN at 1000 ROIs (ablation) | k-GNN · HCP-Gender | accuracy: 82.13 -> 61.57 | Hurt |
| add residual connections with message passing (GNN*) | GNN · HCP-Gender | accuracy: 86.67 -> 89.07 | Helped |
| GNN* versus best standard GNN | GNN* · HCP-Age | accuracy: 44.98 -> 50.23 | Helped |
| GNN* versus best standard GNN on regression | GNN* · HCP-WM | MAE: 0.789 -> 0.751 | Helped |
| GNN versus 3-layer NN on classification | standard GNNs · HCP-Task | accuracy: 97.78 -> 95.2 | Mixed |
Closest papers by meaning
- Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization (ICML 2024 · similarity 0.88)
- $\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes (NeurIPS 2024 · similarity 0.88)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.88)
- NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders (ICML 2025 · similarity 0.88)
- Long-range Brain Graph Transformer (NeurIPS 2024 · similarity 0.87)
- BrainOOD: Out-of-distribution Generalizable Brain Network Analysis (ICLR 2025 · 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.