English

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Machine Learning 2023-02-08 v2 Artificial Intelligence

Abstract

Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed method can not only successfully learn the clean target distribution from a dirty dataset but also can estimate the underlying noise pattern. To this end, we leverage a mixture-of-experts model that can distinguish two different types of predictive uncertainty, aleatoric and epistemic uncertainty. We show that the ability to estimate the uncertainty plays a significant role in elucidating the corruption patterns as these two objectives are tightly intertwined. We also present a novel validation scheme for evaluating the performance of the corruption pattern estimation. Our proposed method is extensively assessed in terms of both robustness and corruption pattern estimation through a number of domains, including computer vision and natural language processing.

Keywords

Cite

@article{arxiv.2111.01632,
  title  = {Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation},
  author = {Jeongeun Park and Seungyoun Shin and Sangheum Hwang and Sungjoon Choi},
  journal= {arXiv preprint arXiv:2111.01632},
  year   = {2023}
}