Research map / Graph learning / Graph self-supervised learning
Causal Subgraphs and Information Bottlenecks: Redefining OOD Robustness in Graph Neural Networks
Weizhi An, Wenliang Zhong, Feng Jiang, Hehuan Ma, Junzhou Huang
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 environment-guided invariance principle to CSIB (ablation) | CSIB · CMNIST-color | accuracy: 16.1% drop without it | Improved |
| add information bottleneck constraint (GIB) to CSIB (ablation) | CSIB · CMNIST-color | accuracy | Improved |
| add invariance principle and GIB to CSIB (ablation) | CSIB · GOOD-HIV scaffold and size | ROC-AUC | Improved |
| set lambda (information bottleneck weight) too high or too low (ablation) | CSIB · Motif-base, Motif-size, CMNIST | accuracy | Hurt |
| increase beta to 0.1 and 1 (ablation) | CSIB · Motif-base, Motif-size, CMNIST | accuracy | Mixed |
| use CSIB instead of prior best on Motif-size | GIN backbone · GOOD-Motif size | accuracy: 54.13 -> 60.99 | Improved |
| use CSIB on Motif-base | GIN backbone · GOOD-Motif base | accuracy: 71.47 -> 70.18 | No clear effect |
Closest papers by meaning
- Dissecting the Failure of Invariant Learning on Graphs (NeurIPS 2024 · similarity 0.90)
- Out-of-Distribution Generalization on Graphs via Progressive Inference (AAAI 2025 · similarity 0.90)
- Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization (NeurIPS 2025 · similarity 0.90)
- Subgraph Aggregation for Out-of-Distribution Generalization on Graphs (AAAI 2025 · similarity 0.90)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.89)
- Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts (ICML 2025 · similarity 0.89)
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.
