.png){kind=icon}
.png){kind=icon}
Return
Label Correction via Contrastive Embedding for Noisy Multi-Label Learning
.png){kind=icon}
PRE
AI
A
H
W
W
DOI：10.1109/tbdata.2026.3668645.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-label learning plays a crucial role in numerous real-world applications, where each instance may be associated with multiple semantic labels. However, in practical scenarios, label noise is widespread and poses a significant challenge, as it can simultaneously distort multiple labels due to ambiguous annotations, human fatigue, or automated labeling inaccuracies. While considerable progress has been made in developing noise-robust methods for single-label learning, addressing noise in multi-label settings remains substantially more challenging due to the intricate interplay among multiple potentially corrupted labels. This underscores the pressing need for effective label correction strategies tailored to noisy multi-label learning. To address this gap, we propose a latent contrastive embedding framework designed for noisy multi-label scenarios. The approach not only learns robust feature representations through supervised contrastive learning but also dynamically identifies clean labels via a small-loss guided sample selection strategy. Moreover, the embedding and label correction processes are jointly optimized, allowing the model to capture the semantic structure of both features and labels under noisy conditions. Specifically, we adopt a small-loss criterion to distinguish clean from noisy samples during the early training phase. In addition, a balanced loss is introduced to mitigate the effects of label imbalance and sample difficulty. Finally, comprehensive experiments conducted under various patterns and levels of label noise demonstrate the superior robustness and generalization ability of the proposed method in noisy multi-label classification tasks.
Keywords:
Multi-label learning
noisy labels
label propagation
label correction
and sample selection
Journal
I
IF:
5.7
Papers:
834
Citations:
3.0K
Organization
Cited Papers