Elucidating robust learning with uncertainty-aware corruption pattern estimation

Jeongeun Park, Seungyoun Shin, Sangheum Hwang, Sungjoon Choi

Abstract: Highlights•We propose a simple yet effective robust learning method leveraging a mixture-of-experts model on various noise settings.•The proposed method can not only robustly learn from noisy data but can also discover the setdependent underlying noise pattern (i.e., the noise transition matrix) as well as the two types of predictive uncertainties (i.e., aleatoric and epistemic uncertainty) within the dataset.•We present a novel evaluation scheme for validating the set-dependent corruption pattern estimation performance.

External IDs:doi:10.1016/j.patcog.2023.109387