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

被引:0
|
作者
Chen, Pengfei [1 ]
Ye, Junjie [2 ]
Chen, Guangyong [3 ]
Zhao, Jingwei [2 ]
Heng, Pheng-Ann [1 ,3 ]
机构
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[2] VIVO AI Lab, Shenzhen, Peoples R China
[3] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Virtual Real & Human Interact Te, Shenzhen, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Supervised learning under label noise has seen numerous advances recently, while existing theoretical findings and empirical results broadly build up on the class-conditional noise (CCN) assumption that the noise is independent of input features given the true label. In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption.The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN). To stimulate the development of theory and methodology on IDN, we formalize an algorithm to generate controllable IDN and present both theoretical and empirical evidence to show that IDN is semantically meaningful and challenging. As a primary attempt to combat IDN, we present a tiny algorithm termed self-evolution average label (SEAL), which not only stands out under IDN with various noise fractions, but also improves the generalization on real-world noise benchmark Clothing1M. Our code is released. Notably, our theoretical analysis in Section 2 provides rigorous motivations for studying IDN, which is an important topic that deserves more research attention in future.
引用
收藏
页码:11442 / 11450
页数:9
相关论文
共 22 条
  • [1] Fair Classification with Instance-dependent Label Noise
    Wu, Songhua
    Gong, Mingming
    Han, Bo
    Liu, Yang
    Liu, Tongliang
    CONFERENCE ON CAUSAL LEARNING AND REASONING, VOL 177, 2022, 177
  • [2] A Parametrical Model for Instance-Dependent Label Noise
    Yang, Shuo
    Wu, Songhua
    Yang, Erkun
    Han, Bo
    Liu, Yang
    Xu, Min
    Niu, Gang
    Liu, Tongliang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (12) : 14055 - 14068
  • [3] Class-Conditional Label Noise in Astroparticle Physics
    Bunse, Mirko
    Pfahler, Lukas
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE AND DEMO TRACK, ECML PKDD 2023, PT VI, 2023, 14174 : 19 - 35
  • [4] Part-dependent Label Noise: Towards Instance-dependent Label Noise
    Xia, Xiaobo
    Liu, Tongliang
    Han, Bo
    Wang, Nannan
    Gong, Mingming
    Liu, Haifeng
    Niu, Gang
    Tao, Dacheng
    Sugiyama, Masashi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [5] Instance-dependent Label Distribution Estimation for Learning with Label Noise
    Liao, Zehui
    Hu, Shishuai
    Xie, Yutong
    Xia, Yong
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, : 2568 - 2580
  • [6] Hypothesis Testing for Class-Conditional Label Noise
    Poyiadzi, Rafael
    Yang, Weisong
    Twomey, Niall
    Santos-Rodriguez, Raul
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT III, 2023, 13715 : 171 - 186
  • [7] An instance-dependent simulation framework for learning with label noise
    Keren Gu
    Xander Masotto
    Vandana Bachani
    Balaji Lakshminarayanan
    Jack Nikodem
    Dong Yin
    Machine Learning, 2023, 112 : 1871 - 1896
  • [8] An instance-dependent simulation framework for learning with label noise
    Gu, Keren
    Masotto, Xander
    Bachani, Vandana
    Lakshminarayanan, Balaji
    Nikodem, Jack
    Yin, Dong
    MACHINE LEARNING, 2023, 112 (06) : 1871 - 1896
  • [9] Leveraging an Alignment Set in Tackling Instance-Dependent Label Noise
    Tjandra, Donna
    Wiens, Jenna
    CONFERENCE ON HEALTH, INFERENCE, AND LEARNING, VOL 209, 2023, 209 : 477 - +
  • [10] Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration
    Zhang, Manyi
    Ren, Yuxin
    Wang, Zihao
    Yuan, Chun
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 4635 - 4644