Timezone: »

 
Poster
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Yongqiang Chen · Yonggang Zhang · Yatao Bian · Han Yang · MA Kaili · Binghui Xie · Tongliang Liu · Bo Han · James Cheng

@

Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.g., images), studies on graph data are still limited. Different from images, the complex nature of graphs poses unique challenges to adopting the invariance principle. In particular, distribution shifts on graphs can appear in a variety of forms such as attributes and structures, making it difficult to identify the invariance. Moreover, domain or environment partitions, which are often required by OOD methods on Euclidean data, could be highly expensive to obtain for graphs. To bridge this gap, we propose a new framework, called Causality Inspired Invariant Graph LeArning (CIGA), to capture the invariance of graphs for guaranteed OOD generalization under various distribution shifts. Specifically, we characterize potential distribution shifts on graphs with causal models, concluding that OOD generalization on graphs is achievable when models focus only on subgraphs containing the most information about the causes of labels. Accordingly, we propose an information-theoretic objective to extract the desired subgraphs that maximally preserve the invariant intra-class information. Learning with these subgraphs is immune to distribution shifts. Extensive experiments on 16 synthetic or real-world datasets, including a challenging setting -- DrugOOD, from AI-aided drug discovery, validate the superior OOD performance of CIGA.

Keywords: Drug Discovery · graph neural networks · out-of-distribution generalization · Graph Representation Learning · invariant learning · causal representation learning
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

Yongqiang Chen (The Chinese University of Hong Kong)
Yonggang Zhang (Hong Kong Baptist University)
Yatao Bian (Tencent AI Lab)
Han Yang (Department of Computer Science and Engineering, The Chinese University of Hong Kong)
MA Kaili (CUHK)
Binghui Xie (Fudan University)
Tongliang Liu (The University of Sydney)
Bo Han (HKBU / RIKEN)
James Cheng (The Chinese University of Hong Kong)

More from the Same Authors