---
title: "Meta Label Correction with Generalization Regularizer"
authors:
  - "Tao Tong"
  - "Yujie Mo"
  - "Yucheng Xie"
  - "Songyue Cai"
  - "Xiaoshuang Shi"
  - "Xiaofeng Zhu"
doi: "10.24963/ijcai.2025/698"
url: "https://ijcai.org/proceedings/2025/698"
pdf: "https://ijcai.org/proceedings/2025/0698.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "6272-6280"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Weakly supervised learning"
  - "Machine Learning: ML: Meta-learning"
  - "Machine Learning: ML: Classification"
---

# Meta Label Correction with Generalization Regularizer

Tao Tong, Yujie Mo, Yucheng Xie, Songyue Cai, Xiaoshuang Shi, Xiaofeng Zhu

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 6272-6280. DOI: [10.24963/ijcai.2025/698](https://doi.org/10.24963/ijcai.2025/698)

## Abstract

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.