English

Understanding Domain Generalization: A Noise Robustness Perspective

Machine Learning 2024-03-19 v2 Computer Vision and Pattern Recognition

Abstract

Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard benchmarks. To better understand this phenomenon, we investigate whether there are benefits of DG algorithms over ERM through the lens of label noise. Specifically, our finite-sample analysis reveals that label noise exacerbates the effect of spurious correlations for ERM, undermining generalization. Conversely, we illustrate that DG algorithms exhibit implicit label-noise robustness during finite-sample training even when spurious correlation is present. Such desirable property helps mitigate spurious correlations and improve generalization in synthetic experiments. However, additional comprehensive experiments on real-world benchmark datasets indicate that label-noise robustness does not necessarily translate to better performance compared to ERM. We conjecture that the failure mode of ERM arising from spurious correlations may be less pronounced in practice.

Keywords

Cite

@article{arxiv.2401.14846,
  title  = {Understanding Domain Generalization: A Noise Robustness Perspective},
  author = {Rui Qiao and Bryan Kian Hsiang Low},
  journal= {arXiv preprint arXiv:2401.14846},
  year   = {2024}
}

Comments

Accepted to the 12th International Conference on Learning Representations (ICLR 2024). Code is available at https://github.com/qiaoruiyt/NoiseRobustDG

R2 v1 2026-06-28T14:28:06.500Z