Meta Label Correction with Generalization Regularizer

Deep neural networks can easily lead to the over-fitting issue due to the influence of noisy labels. However, previous label correction methods for dealing with noisy labels often need expensive computation cost to achieve effectiveness and ignore the generalization ability of the model. To address these issues, in this paper, we propose a new meta-based self-correction method to achieve accurate filtering of noisy labels and to enhance the generalization ability of the label correction model. Specifically, we first investigate a new gradient score method to filter noisy labels with less computation cost, and then theoretically design a new generalization regularizer into the meta-learner and the base learner, for correcting noisy labels as well as achieving the generalization ability. Experimental results on real datasets verify the effectiveness of our proposed method in terms of different classification tasks.

Authors

• Tao Tong University of Electronic Science and Technology of China
• Yujie Mo School of Computer Science and Engineering, University of Electronic Science and Technology of China
• Yucheng Xie
• Songyue Cai
• Xiaoshuang Shi School of Computer Science and Engineering, University of Electronic Science and Technology of China
• Xiaofeng Zhu Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University School of Computer Science and Engineering, University of Electronic Science and Technology of China

Keywords

• Machine Learning: ML: Classification
• Machine Learning: ML: Meta-learning
• Machine Learning: ML: Weakly supervised learning