Learning to Clean: Reinforcement Learning for Noisy Label Correction
This addresses the challenge of noisy labels degrading model performance in machine learning, representing a novel method for a known bottleneck.
The paper tackles the problem of learning with noisy labels by introducing a reinforcement learning framework for label correction, and it demonstrates that this approach consistently outperforms existing state-of-the-art methods on multiple benchmark datasets.
The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy label correction as a reinforcement learning (RL) problem. The proposed approach, Reinforcement Learning for Noisy Label Correction (RLNLC), defines a comprehensive state space representing data and their associated labels, an action space that indicates possible label corrections, and a reward mechanism that evaluates the efficacy of label corrections. RLNLC learns a deep feature representation based policy network to perform label correction through reinforcement learning, utilizing an actor-critic method. The learned policy is subsequently deployed to iteratively correct noisy training labels and facilitate the training of the prediction model. The effectiveness of RLNLC is demonstrated through extensive experiments on multiple benchmark datasets, where it consistently outperforms existing state-of-the-art techniques for learning with noisy labels.