Research map / Graph learning / Graph self-supervised learning
Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders
Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf, Ke Li
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 micro-macro (MM) graph statistic modeling to GraphVAE | GraphVAE · Triangle Grid | MMD RBF: 0.23 -> 0.17 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · Lobster | F1 PR: 78.48 -> 100.00 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · Grid | F1 PR: 75.52 -> 97.09 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · ogbg-molbbbp | MMD RBF: 0.20 -> 0.02 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · ogbg-molbbbp | F1 PR: 54.53 -> 93.78 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · Protein | MMD RBF: 0.10 -> 0.03 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · statistics-based MMD on synthetic and real graphs | MMD | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · MUTAG | MMD RBF: 0.09 -> 0.07 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · PTC | MMD RBF: 0.53 -> 0.04 | Improved |
| add micro-macro modeling to GraphVAE | GraphVAE · QM9 | F1 PR: 97.28 -> 96.16 | Hurt |
| train GraphVAE with beta-VAE (beta=16) instead of macro statistics (ablation) | GraphVAE · Lobster and ogbg-molbbbp | statistics MMD | No clear effect |
| use a single target statistic (e.g. triangle count) instead of all three (ablation) | GraphVAE-MM · Lobster and ogbg-molbbbp | statistics MMD | Hurt |
Closest papers by meaning
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.87)
- Efficient and Scalable Graph Generation through Iterative Local Expansion (ICLR 2024 · similarity 0.87)
- Geometric Generative Modeling with Noise-Conditioned Graph Networks (ICML 2025 · similarity 0.87)
- On the Role of Edge Dependency in Graph Generative Models (ICML 2024 · similarity 0.87)
- Rethinking Graph Masked Autoencoders through Alignment and Uniformity (AAAI 2024 · similarity 0.87)
- HiGen: Hierarchical Graph Generative Networks (ICLR 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.
