Multiplicative Reweighting for Robust Neural Network Optimization
This addresses robustness issues in neural networks for applications with noisy data, but it is incremental as it adapts an existing method to a new context.
The paper tackles the problem of neural network performance degradation due to noisy labels during training by proposing multiplicative reweighting based on multiplicative weights updates, showing improved accuracy on datasets like CIFAR-10, CIFAR-100, and Clothing1M.
Neural networks are widespread due to their powerful performance. Yet, they degrade in the presence of noisy labels at training time. Inspired by the setting of learning with expert advice, where multiplicative weights (MW) updates were recently shown to be robust to moderate data corruptions in expert advice, we propose to use MW for reweighting examples during neural networks optimization. We theoretically establish the convergence of our method when used with gradient descent and prove its advantages in 1d cases. We then validate empirically our findings for the general case by showing that MW improves neural networks' accuracy in the presence of label noise on CIFAR-10, CIFAR-100 and Clothing1M. We also show the impact of our approach on adversarial robustness.