Part-dependent Label Noise: Towards Instance-dependent Label Noise

Xiaobo Xia, Tongliang Liu*, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, Dacheng Tao, Masashi Sugiyama

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

134 Citations (Scopus)


Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by decomposing them into parts. Annotators are therefore more likely to annotate instances based on the parts rather than the whole instances, where a wrong mapping from parts to classes may cause the instance-dependent label noise. Motivated by this human cognition, in this paper, we approximate the instance-dependent label noise by exploiting \textit{part-dependent} label noise. Specifically, since instances can be approximately reconstructed by a combination of parts, we approximate the instance-dependent \textit{transition matrix} for an instance by a combination of the transition matrices for the parts of the instance. The transition matrices for parts can be learned by exploiting anchor points (i.e., data points that belong to a specific class almost surely). Empirical evaluations on synthetic and real-world datasets demonstrate our method is superior to the state-of-the-art approaches for learning from the instance-dependent label noise.
Original languageEnglish
Title of host publication34th Conference on Neural Information Processing Systems (NeurIPS 2020)
EditorsH. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, H. Lin
PublisherNeural Information Processing Systems Foundation
Number of pages14
ISBN (Print)9781713829546
Publication statusPublished - 6 Dec 2020
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258
NameNeurIPS Proceedings


Conference34th Conference on Neural Information Processing Systems, NeurIPS 2020
Internet address


Dive into the research topics of 'Part-dependent Label Noise: Towards Instance-dependent Label Noise'. Together they form a unique fingerprint.

Cite this