AI Paper Atlas

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

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
GCIB vs best baseline IBCSIBCS · SPMotif-0.3accuracy: 73.17 -> 75.07Improved
GCIB vs best baseline IBCSIBCS · MNIST-75spaccuracy: 25.46 -> 26.65Improved
GCIB vs Info-IGLInfo-IGL · Graph-SST2accuracy: 83.47 -> 85.34Improved
GCIB vs ERM on average real-world datasetsERM · Real-world datasetsaverageImproved
GCIB vs IBCS under DrugOOD EC50-Assay General noiseIBCS · DrugOOD EC50-Assay GeneralROC-AUC: 67.15 -> 70.11Improved
Causal intervention objective vs plain IB baselines under noise (GIB vs ERM)ERM · DrugOOD EC50-Assay GeneralROC-AUC: 67.34 -> 65.52Hurt
Remove any one of the three loss terms of Eq. 14 (GCIB-I, II, III) (ablation)GCIB · Spurious-Motif and real-world datasetsaccuracy/AUCImproved
Vary lambda and beta (ablation)GCIB · Core-EC50-AssayAUC: 76.58 to 78.82No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy