Research map / Graph learning / Graph self-supervised learning
Automated Self-Supervised Learning for Graphs
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 |
|---|---|---|---|
| Search task weights across five SSL tasks using pseudo-homophily | GCN graph representations · WikiCS | NMI: 0.341±0.01 -> 0.366±0.01 | Helped |
| Search task weights across five SSL tasks using pseudo-homophily | GCN graph representations · Photo | NMI: 0.509±0.01 -> 0.560±0.04 | Helped |
| Search task weights across five SSL tasks using pseudo-homophily | GCN graph representations · Computers | accuracy (%): 87.26±0.15 -> 88.18±0.43 | Helped |
| Search task weights across five SSL tasks using pseudo-homophily | GCN graph representations · ogbn-arxiv | accuracy (%): 67.95±0.56 -> 69.13±0.04 | Helped |
| Assign task weights randomly instead of searching them (ablation) | five-task SSL combination on Citeseer · Citeseer | NMI: 0.439±0.00 -> 0.398±0.01 | Hurt |
| Assign all five task weights equally instead of searching them (ablation) | five-task SSL combination on Citeseer · Citeseer | NMI: 0.439±0.00 -> 0.408±0.00 | Hurt |
| Assign task weights randomly instead of searching them (ablation) | five-task SSL combination on Citeseer · Citeseer | accuracy (%): 71.64±0.44 -> 70.64±0.07 | Hurt |
| Assign all five task weights equally instead of searching them (ablation) | five-task SSL combination on Citeseer · Citeseer | accuracy (%): 71.64±0.44 -> 70.80±0.31 | Hurt |
Closest papers by meaning
- Exploring Correlations of Self-Supervised Tasks for Graphs (ICML 2024 · similarity 0.89)
- Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering (AAAI 2024 · similarity 0.88)
- Empowering Dual-Level Graph Self-Supervised Pretraining with Motif Discovery (AAAI 2024 · similarity 0.87)
- Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum (ICML 2025 · similarity 0.87)
- Equivalence is All: A Unified View for Self-supervised Graph Learning (ICML 2025 · similarity 0.87)
- From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble (ICML 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.