Improve Noise Tolerance of Robust Loss via Noise-Awareness

TL;DR

This paper introduces a meta-learning approach to adaptively set instance-dependent hyperparameters in robust loss functions, significantly improving noise tolerance and generalization in learning with noisy labels.

Contribution

It proposes a novel Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster) that learns hyperparameters per sample, enhancing robustness over existing methods that use fixed hyperparameters.

Findings

Improved noise robustness across four state-of-the-art robust loss functions.

Demonstrated superior performance and generalization in noisy label scenarios.

The method effectively adapts hyperparameters to individual sample noise properties.

Abstract

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current approaches for designing robust losses involve the introduction of noise-robust factors, i.e., hyperparameters, to control the trade-off between noise robustness and learnability. However, finding suitable hyperparameters for different datasets with noisy labels is a challenging and time-consuming task. Moreover, existing robust loss methods usually assume that all training samples share common hyperparameters, which are independent of instances. This limits the ability of these methods to distinguish the individual noise properties of different samples and overlooks the varying contributions of diverse training samples in helping models understand underlying patterns. To address above issues, we propose to assemble robust loss with instance-dependent hyperparameters to improve their noise tolerance with theoretical guarantee. To achieve setting such instance-dependent hyperparameters for robust loss, we propose a meta-learning method which is capable of adaptively learning a hyperparameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity). Through mutual amelioration between hyperparameter prediction function and classifier parameters in our method, both of them can be simultaneously finely ameliorated and coordinated to attain solutions with good generalization capability. Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.