Meta-Causal Feature Learning for Out-of-Distribution Generalization

TL;DR

This paper introduces BMCL, a novel framework that enhances out-of-distribution generalization by generating balanced data subsets and meta-learning invariant features, outperforming existing methods.

Contribution

The paper proposes a balanced meta-causal learner with a self-learned partitioning algorithm and a meta-causal feature learning module to improve invariant feature extraction from heterogeneous data.

Findings

BMCL effectively identifies class-invariant visual regions.

It improves OOD generalization performance over state-of-the-art methods.

Experiments on NICO++ dataset validate its effectiveness.

Abstract

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.