Partial Multi-Label Learning With Noisy Label Identification

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 7; pp. 3676 - 3687
• Main Authors: Xie, Ming-Kun, Huang, Sheng-Jun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: candidate label set; Correlation; Crowdsourcing; Labeling; Labels; Learning; multi-instance multi-label learning; Multi-lable learning; Noise measurement; noisy label identification; partial multi-label learning; Phase locked loops; Task analysis; Training
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2021.3059290

Partial multi-label learning (PML) deals with problems where each instance is assigned with a candidate label set, which contains multiple relevant labels and some noisy labels. Recent studies usually solve PML problems with the disambiguation strategy, which recovers ground-truth labels from the candidate label set by simply assuming that the noisy labels are generated randomly. In real applications, however, noisy labels are usually caused by some ambiguous contents of the example. Based on this observation, we propose a partial multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels. The two objectives are formalized in a unified framework with trace norm and <inline-formula><tex-math notation="LaTeX">\ell _1</tex-math> <mml:math><mml:msub><mml:mi>ℓ</mml:mi><mml:mn>1</mml:mn></mml:msub></mml:math><inline-graphic xlink:href="xie-ieq1-3059290.gif"/> </inline-formula> norm regularizers. Under the supervision of the observed noise-corrupted label matrix, the multi-label classifier and noisy label identifier are jointly optimized by incorporating the label correlation exploitation and feature-induced noise model. Furthermore, by mapping each bag to a feature vector, we extend PML-NI method into multi-instance multi-label learning by identifying noisy labels based on ambiguous instances. A theoretical analysis of generalization bound and extensive experiments on multiple data sets from various real-world tasks demonstrate the effectiveness of the proposed approach.