Research map / Graph learning / Graph algorithms and clustering
Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience
Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar, Anjany Sekuboyina, Mihail Todorov, Georgios Kaissis, Ali Ertürk, Stephan Günnemann, bjoern menze
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 SEAL with its subgraph labeling trick instead of the strongest simple GNN baseline, GraphSAGE | Link prediction · BALBc-1 | ROC AUC: 59.23 -> 90.96 | Improved |
| Add Node2Vec embeddings to GCN (ablation) | GCN link predictor · BALBc-1 | ROC AUC: 50.72 -> 51.13 | No clear effect |
| Add Node2Vec embeddings to GraphSAGE (ablation) | GraphSAGE link predictor · BALBc-1 | ROC AUC: 59.23 -> 52.88 | Hurt |
| Use GraphSAGE instead of GCN | Link prediction · BALBc-1 | ROC AUC: 50.72 -> 59.23 | Improved |
| Use Cluster-GCN instead of GCN | Vessel classification · BALBc-1 | weighted F1: $75.75$ -> $86.06$ | Improved |
| Use GraphSAGE instead of GCN | Vessel classification · BALBc-1 | weighted F1: $75.75$ -> $81.98$ | Improved |
| Add Node2Vec to SpecMLP-W + C&S (ablation) | Vessel classification · BALBc-1 | weighted F1: $84.55$ -> $80.63$ | Hurt |
| Use graph neural networks rather than non-graph methods | Vessel classification · BALBc-1 | ROC AUC: $57.79$ -> $77.18$ | Improved |
| Use graph neural networks rather than non-graph methods | Vessel classification · BALBc-1 | balanced accuracy: $41.72$ -> $71.33$ | Improved |
Closest papers by meaning
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics (NeurIPS 2023 · similarity 0.90)
- VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation (ECCV 2026 · similarity 0.89)
- $\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes (NeurIPS 2024 · similarity 0.86)
- Long-range Brain Graph Transformer (NeurIPS 2024 · similarity 0.86)
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation (CVPR 2025 · similarity 0.85)
- Biologically Plausible Brain Graph Transformer (ICLR 2025 · 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.
