Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization
This addresses the problem of robust graph learning under distribution shifts for applications like social networks or molecular graphs, representing a novel method for a known bottleneck.
The paper tackles graph out-of-distribution generalization by proposing a method that incorporates label and environment causal independence to identify causal and invariant subgraphs, achieving significant performance improvements over prior methods on synthetic and real-world datasets.
We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD algorithms either rely on restricted assumptions or fail to exploit environment information in training data. In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs. We further develop an adversarial training strategy to jointly optimize these two properties for causal subgraph discovery with theoretical guarantees. Extensive experiments and analysis show that LECI significantly outperforms prior methods on both synthetic and real-world datasets, establishing LECI as a practical and effective solution for graph OOD generalization. Our code is available at https://github.com/divelab/LECI.