The Final Ascent: When Bigger Models Generalize Worse on Noisy-Labeled Data

Increasing the size of overparameterized neural networks has been shown to improve their generalization performance. However, real-world datasets often contain a significant fraction of noisy labels, which can drastically harm the performance of the models trained on them. In this work, we study how neural networks' test loss changes with model size when the training set contains noisy labels. We show that under a sufficiently large noise-to-sample size ratio, generalization error eventually increases with model size. First, we provide a theoretical analysis on random feature regression and show that this phenomenon occurs as the variance of the generalization loss experiences a second ascent under large noise-to-sample size ratio. Then, we present extensive empirical evidence confirming that our theoretical results hold for neural networks. Furthermore, we empirically observe that the adverse effect of network size is more pronounced when robust training methods are employed to learn from noisy-labeled data. Our results have important practical implications: First, larger models should be employed with extra care, particularly when trained on smaller dataset or using robust learning methods. Second, a large sample size can alleviate the effect of noisy labels and allow larger models to achieve a superior performance even under noise.