Research map / Graph learning / Graph self-supervised learning
Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
Davide Bacciu, Federico Errica, Alessio Micheli
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 |
|---|---|---|---|
| Increase the number of CGMM layers (ablation) | CGMM without pooling · CPDB, AIDS, and MUTAG | accuracy | Improved |
| Continue adding layers after performance reaches a plateau (ablation) | CGMM without pooling · MUTAG | accuracy | Hurt |
| Use pooling to select the best model from randomly initialized candidates at each layer (ablation) | CGMM · Graph classification benchmarks | accuracy | Mixed |
| Concatenate fingerprints from all layers rather than using only the last layer (ablation) | CGMM · MUTAG, CPDB, and AIDS | accuracy | Mixed |
| Use a Jaccard kernel rather than an RBF kernel (ablation) | CGMM · INEX2005 and INEX2006 | test accuracy: 96.60 (0.05) -> 96.73 (0.06); 45.1 (0.2) -> 43.18 (0.3) | Mixed |
Closest papers by meaning
- Quality Measures for Dynamic Graph Generative Models (ICLR 2025 · similarity 0.87)
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · similarity 0.87)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.86)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · similarity 0.86)
- On the Role of Edge Dependency in Graph Generative Models (ICML 2024 · similarity 0.86)
- ICLR: In-Context Learning of Representations (ICLR 2025 · 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.
