Meta-Causal Feature Learning for Out-of-Distribution Generalization
This work addresses out-of-distribution generalization for machine learning systems, presenting an incremental improvement over existing causal methods.
The paper tackles the problem of out-of-distribution generalization by proposing a balanced meta-causal learner (BMCL) to extract invariant features, and experiments on the NICO++ dataset show it effectively identifies class-invariant visual regions for classification.
Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners from multiple data splits, which may incur biased representation learning from imbalanced data distributions and difficulty in invariant feature learning from heterogeneous sources. To address these issues, this paper presents a balanced meta-causal learner (BMCL), which includes a balanced task generation module (BTG) and a meta-causal feature learning module (MCFL). Specifically, the BTG module learns to generate balanced subsets by a self-learned partitioning algorithm with constraints on the proportions of sample classes and contexts. The MCFL module trains a meta-learner adapted to different distributions. Experiments conducted on NICO++ dataset verified that BMCL effectively identifies the class-invariant visual regions for classification and may serve as a general framework to improve the performance of the state-of-the-art methods.