Research map / Graph learning / Graph self-supervised learning
Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles
Li Sun, Zhenhao Huang, Yiding Wang, Qin Chen, Pietro Lio, Philip S. Yu
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 GAUGE (neural vector bundle + Dirichlet loss) instead of best prior GFM | graph foundation models · PubMed (1-shot) | accuracy (%): 56.82 -> 61.26 (vs RiemannGFM) | Improved |
| use GAUGE | GraphAny · Photo (5-shot) | accuracy (%): 78.45 -> 81.33 | Improved |
| use GAUGE | GFT · Roman-empire (5-shot) | accuracy (%): 26.60 -> 26.43 | No clear effect |
| use GAUGE for zero-shot link prediction | best baseline · Facebook zero-shot link prediction | AUC (%): 87.41 -> 93.88 (vs RAGraph) | Improved |
| use GAUGE for zero-shot link prediction | GCOPE · PubMed zero-shot link prediction | AP (%): 61.91 -> 61.40 | Hurt |
| use GAUGE for zero-shot link prediction | SAMGPT · Photo zero-shot link prediction | AUC (%): 92.26 -> 93.04 | Improved |
| use GAUGE for graph isomorphism | SAMGPT · CSL | accuracy (%): 64.17 -> 92.56 | Improved |
| use GAUGE for graph isomorphism | GIN · ZINC12K | MAE: 0.163 -> 0.157 | Improved |
Closest papers by meaning
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.87)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.86)
- Spectro-Riemannian Graph Neural Networks (ICLR 2025 · similarity 0.85)
- GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators (NeurIPS 2026 · similarity 0.85)
- Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning (AAAI 2024 · similarity 0.85)
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 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.
