Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
This work addresses the challenge of noisy labels in machine learning, which is critical for real-world applications where data annotation errors are common, representing an incremental improvement over prior methods.
The paper tackles the problem of learning with noisy labels by proposing a generalized Jensen-Shannon divergence loss that interpolates between cross-entropy and mean absolute error to improve robustness, achieving state-of-the-art results on synthetic and real-world datasets with varying noise rates.
Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE) to improve their learnability. Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter. Furthermore, we make a crucial observation that CE exhibit lower consistency around noisy data points. Based on this observation, we adopt a generalized version of the Jensen-Shannon divergence for multiple distributions to encourage consistency around data points. Using this loss function, we show state-of-the-art results on both synthetic (CIFAR), and real-world (e.g., WebVision) noise with varying noise rates.