Casual Balancing for Domain Generalization
Document Type
Article
Publication Title
arXiv
Abstract
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark. 1 Copyright © 2022, The Authors. All rights reserved.
DOI
10.48550/arXiv.2206.05263
Publication Date
6-10-2022
Keywords
Balancing, Benchmarking, Machine learning
Recommended Citation
X. Wang, M. Saxon, J. Li, H. Zhang, K. Zhang, and W.Y. Zang, "Causal Balancing for Domain Generalization", 2022, doi:10.48550/arXiv.2206.05263
Comments
IR Deposit conditions: non-described