Tackling Instance-Dependent Label Noise with Class Rebalance and Geometric Regularization-Reference-Cited by-同舟云学术

Tackling Instance-Dependent Label Noise with Class Rebalance and Geometric Regularization

Published:2024-08-24 Issue: Volume:34 Page:211-221
ISSN:
Container-title:Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
language:
Short-container-title:

Author:

Cao Shuzhi¹^ORCID,Ruan Jianfei¹^ORCID,Dong Bo²^ORCID,Shi Bin³^ORCID

Affiliation:

1. School of Computer Science and Technology & Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an, China

2. School of Distance Education & Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi'an Jiaotong University, Xi'an, China

3. School of Computer Science and Technology & Ministry of Education Key Lab For Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China

Funder

National Key Research and Development Project of China

Key Research and Development Project in Shaanxi Province

National Science Foundation of China under Grant

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3637528.3671707

Reference46 articles.

1. Understanding and improving early stopping for learning with noisy labels;Bai Yingbin;Advances in Neural Information Processing Systems,2021

2. Antonin Berthon, Bo Han, Gang Niu, Tongliang Liu, and Masashi Sugiyama. 2021. Confidence scores make instance-dependent label-noise learning possible. In International conference on machine learning. PMLR, 825--836.

3. Noise-tolerant learning, the parity problem, and the statistical query model

4. Large-Scale Machine Learning with Stochastic Gradient Descent

5. Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise