Can I read Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization on EtoBox?

Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization by Mao, Wenyu; Wu, Jiancan; Liu, Haoyang; Sui, Yongduo; Wang, Xiang is a scholarly article available to read on EtoBox.

What is Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization about?

Graph out-of-distribution (OOD) generalization remains a major challenge in graph learning since graph neural networks (GNNs) often suffer from severe performance degradation under distribution shifts. Invariant learning, aiming to extract invariant features across varied distributions, has recently emerged as a promising approach for OOD generation. Despite the great success of invariant learning in OOD problems for Euclidean data (i.e., images), the exploration within graph data remains constrained by the complex nature of graphs. Existing studies, such as data augmentation or causal intervention, either suffer from disruptions to invariance during the graph manipulation process or face reliability issues due to a lack of supervised signals for causal parts. In this work, we propose a novel framework, called Invariant Graph Learning based on Information bottleneck theory (InfoIGL), to extract the invariant features of graphs and enhance models' generalization ability to unseen distributions. Specifically, InfoIGL introduces a redundancy filter to compress task-irrelevant information related to environmental factors. Cooperating with our designed multi-level contrastive learning,

Author

Mao, Wenyu; Wu, Jiancan; Liu, Haoyang; Sui, Yongduo; Wang, Xiang

Published

2024

Language

EN