Research map / Graph learning / Graph self-supervised learning
GCIB: Causal Intervention Guided Graph Information Bottleneck Framework
Hangyuan Du, Rong Wang, Lixin Cui, Gaoxia Jiang, Liang Bai, Wenjian Wang
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 |
|---|---|---|---|
| GCIB vs best baseline IBCS | IBCS · SPMotif-0.3 | accuracy: 73.17 -> 75.07 | Improved |
| GCIB vs best baseline IBCS | IBCS · MNIST-75sp | accuracy: 25.46 -> 26.65 | Improved |
| GCIB vs Info-IGL | Info-IGL · Graph-SST2 | accuracy: 83.47 -> 85.34 | Improved |
| GCIB vs ERM on average real-world datasets | ERM · Real-world datasets | average | Improved |
| GCIB vs IBCS under DrugOOD EC50-Assay General noise | IBCS · DrugOOD EC50-Assay General | ROC-AUC: 67.15 -> 70.11 | Improved |
| Causal intervention objective vs plain IB baselines under noise (GIB vs ERM) | ERM · DrugOOD EC50-Assay General | ROC-AUC: 67.34 -> 65.52 | Hurt |
| Remove any one of the three loss terms of Eq. 14 (GCIB-I, II, III) (ablation) | GCIB · Spurious-Motif and real-world datasets | accuracy/AUC | Improved |
| Vary lambda and beta (ablation) | GCIB · Core-EC50-Assay | AUC: 76.58 to 78.82 | No clear effect |
Closest papers by meaning
- Out-of-Distribution Generalization on Graphs via Progressive Inference (AAAI 2025 · similarity 0.88)
- Rethinking Causal Relationships Learning in Graph Neural Networks (AAAI 2024 · similarity 0.88)
- A Recipe for Causal Graph Regression: Confounding Effects Revisited (ICML 2025 · similarity 0.88)
- Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization (NeurIPS 2025 · similarity 0.86)
- RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks (NeurIPS 2024 · similarity 0.86)
- Graph Contrastive Invariant Learning from the Causal Perspective (AAAI 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.
