Research map / Graph learning / Graph self-supervised learning
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
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 |
|---|---|---|---|
| Add ego-semantic descriptors to GraphCL (ablation) | GraphCL on MUV · MUV | performance: 2%-4% | Helped |
| Use second-order rather than first-order ego-semantic descriptors (ablation) | OEPG on MUV · MUV | performance | Helped |
| Concatenate first- and second-order ego-semantic descriptors (ablation) | OEPG on MUV · MUV | performance | Helped |
| Add ego-semantic descriptors (ablation) | OEPG · RDT-B | accuracy: +2.2 | Helped |
| Add ego-semantic descriptors (ablation) | OEPG · WikiCS | accuracy: +2.3 | Helped |
| Add omni-granular normalization (ablation) | OEPG with ego-semantic descriptors · RDT-B | accuracy: +1.2 | Helped |
| Add omni-granular normalization (ablation) | OEPG with ego-semantic descriptors · WikiCS | accuracy: +1.6 | Helped |
| Add specialized pretext tasks (ablation) | OEPG with omni-granular normalization · RDT-B | accuracy: +0.7 | Helped |
| Add specialized pretext tasks (ablation) | OEPG with omni-granular normalization · WikiCS | accuracy: +0.8 | Helped |
| Add cross-iteration momentum update (ablation) | OEPG with specialized pretext tasks · RDT-B | accuracy: +0.6 | Helped |
| Add cross-iteration momentum update (ablation) | OEPG with specialized pretext tasks · WikiCS | accuracy: +0.5 | Helped |
| Increase ego-semantic hierarchy beyond 4 (ablation) | OEPG on MUV · MUV | performance | Hurt |
Closest papers by meaning
- From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble (ICML 2024 · similarity 0.88)
- Decoupled Self-supervised Learning for Graphs (NeurIPS 2022 · similarity 0.88)
- Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization (ICML 2024 · similarity 0.88)
- Equivalence is All: A Unified View for Self-supervised Graph Learning (ICML 2025 · similarity 0.87)
- Graph Classification via Reference Distribution Learning: Theory and Practice (NeurIPS 2024 · similarity 0.86)
- Core Knowledge Learning Framework for Graph (AAAI 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.