LGMar 21, 2023

Dynamics-Aware Loss for Learning with Label Noise

arXiv:2303.11562v320 citationsh-index: 74Has Code
Originality Incremental advance
AI Analysis

This work addresses label noise for deep learning practitioners, offering an incremental improvement over existing robust loss methods.

The paper tackles the problem of label noise in deep neural networks by proposing a dynamics-aware loss (DAL) that adapts the trade-off between fitting ability and robustness during training, leading to improved performance as demonstrated in experiments.

Label noise poses a serious threat to deep neural networks (DNNs). Employing robust loss functions which reconcile fitting ability with robustness is a simple but effective strategy to handle this problem. However, the widely-used static trade-off between these two factors contradicts the dynamics of DNNs learning with label noise, leading to inferior performance. Therefore, we propose a dynamics-aware loss (DAL) to solve this problem. Considering that DNNs tend to first learn beneficial patterns, then gradually overfit harmful label noise, DAL strengthens the fitting ability initially, then gradually improves robustness. Moreover, at the later stage, to further reduce the negative impact of label noise and combat underfitting simultaneously, we let DNNs put more emphasis on easy examples than hard ones and introduce a bootstrapping term. Both the detailed theoretical analyses and extensive experimental results demonstrate the superiority of our method. Our source code can be found in https://github.com/XiuchuanLi/DAL.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes