Learning Graph Invariance by Harnessing Spuriosity
Yao, Tianjun Chen, Yongqiang Hu, Kai Liu, Tongliang Zhang, Kun Shen, Zhiqiang
Yao, Tianjun
Chen, Yongqiang
Hu, Kai
Liu, Tongliang
Zhang, Kun
Shen, Zhiqiang
Supervisor
Department
Machine Learning
Embargo End Date
Type
Poster
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Recently, graph invariant learning has become the _de facto_ approach to tackle the Out-of-Distribution (OOD) generalization failure in graph representation learning. They generically follow the framework of invariant risk minimization to capture the invariance of graph data from different environments. Despite some success, it remains unclear to what extent existing approaches have captured invariant features for OOD generalization on graphs. In this work, we find that representative OOD methods such as IRM and VRex, and their variants on graph invariant learning may have captured a limited set of invariant features. To tackle this challenge, we propose LIRS, a novel learning framework designed to **L**earn graph **I**nvariance by **R**emoving **S**purious features. Different from most existing approaches that _directly_ learn the invariant features, LIRS takes an _indirect_ approach by first learning the spurious features and then removing them from the ERM-learned features, which contains both spurious and invariant features. We demonstrate that learning the invariant graph features in an _indirect_ way can learn a more comprehensive set of invariant features. Moreover, our proposed method outperforms the second-best method by as much as 25.50% across all competitive baseline methods, highlighting its effectiveness in learning graph invariant features.
Citation
“ICLR Poster Learning Graph Invariance by Harnessing Spuriosity.” Accessed: Jun. 24, 2025. [Online]. Available: https://iclr.cc/virtual/2025/poster/29448
Source
The Thirteenth International Conference on Learning Representations (ICLR 2025)
Conference
The Thirteenth International Conference on Learning Representations (ICLR 2025)
Keywords
Subjects
Source
The Thirteenth International Conference on Learning Representations (ICLR 2025)
Publisher
International Conference on Learning Representations, ICLR