Do We Always Need to Penalize Variance of Losses for Learning with Label Noise?

Yexiong Lin, Yu Yao, Yuxuan Du, Jun Yu, Bo Han, Mingming Gong, Tongliang Liu

Abstract: Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels. Intuitively, when there is a finite training sample, penalizing the variance of losses will improve the stability and generalization of the algorithms. Interestingly, we found that the variance of losses sometimes needs to be increased for the problem of learning with noisy labels. Specifically, increasing the variance of losses would boost the memorization effect and reduce the harmfulness of incorrect labels. Regularizers can be easily designed to increase the variance of losses and be plugged in many existing algorithms. Empirically, the proposed method by increasing the variance of losses could improve the generalization ability of baselines on both synthetic and real-world datasets.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning