SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
This work addresses the issue of memorization in noisy label learning for machine learning practitioners, offering an incremental improvement over existing methods.
The paper tackles the problem of overfitting in deep networks trained on noisy labels by proposing SIGUA, a method that combines gradient descent on good data with reduced gradient ascent on bad data, which significantly improves the performance of two base learning methods.
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels, many learning methods in this area still suffer overfitting due to undesired memorization. In this paper, to relieve this issue, we propose stochastic integrated gradient underweighted ascent (SIGUA): in a mini-batch, we adopt gradient descent on good data as usual, and learning-rate-reduced gradient ascent on bad data; the proposal is a versatile approach where data goodness or badness is w.r.t. desired or undesired memorization given a base learning method. Technically, SIGUA pulls optimization back for generalization when their goals conflict with each other; philosophically, SIGUA shows forgetting undesired memorization can reinforce desired memorization. Experiments demonstrate that SIGUA successfully robustifies two typical base learning methods, so that their performance is often significantly improved.