Shift-Robust Molecular Relational Learning with Causal Substructure
This addresses robustness issues in predicting molecular interactions for applications in molecular sciences, representing a novel method for a known bottleneck.
The paper tackles distributional shift in molecular relational learning by proposing CMRL, which detects causally-related substructures to improve robustness; experiments show it outperforms state-of-the-art baselines on real-world and synthetic datasets.
Recently, molecular relational learning, whose goal is to predict the interaction behavior between molecular pairs, got a surge of interest in molecular sciences due to its wide range of applications. In this work, we propose CMRL that is robust to the distributional shift in molecular relational learning by detecting the core substructure that is causally related to chemical reactions. To do so, we first assume a causal relationship based on the domain knowledge of molecular sciences and construct a structural causal model (SCM) that reveals the relationship between variables. Based on the SCM, we introduce a novel conditional intervention framework whose intervention is conditioned on the paired molecule. With the conditional intervention framework, our model successfully learns from the causal substructure and alleviates the confounding effect of shortcut substructures that are spuriously correlated to chemical reactions. Extensive experiments on various tasks with real-world and synthetic datasets demonstrate the superiority of CMRL over state-of-the-art baseline models. Our code is available at https://github.com/Namkyeong/CMRL.