AI Paper Atlas

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

ECCV 2024 · Graph learning › Graph self-supervised learning · approach: Graph out-of-distribution generalization · 5 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
add environment-guided invariance principle to CSIB (ablation)CSIB · CMNIST-coloraccuracy: 16.1% drop without itImproved
add information bottleneck constraint (GIB) to CSIB (ablation)CSIB · CMNIST-coloraccuracyImproved
add invariance principle and GIB to CSIB (ablation)CSIB · GOOD-HIV scaffold and sizeROC-AUCImproved
set lambda (information bottleneck weight) too high or too low (ablation)CSIB · Motif-base, Motif-size, CMNISTaccuracyHurt
increase beta to 0.1 and 1 (ablation)CSIB · Motif-base, Motif-size, CMNISTaccuracyMixed
use CSIB instead of prior best on Motif-sizeGIN backbone · GOOD-Motif sizeaccuracy: 54.13 -> 60.99Improved
use CSIB on Motif-baseGIN backbone · GOOD-Motif baseaccuracy: 71.47 -> 70.18No 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