Partial Multi-Label Learning with Missing Labels via Feature-Label Disentanglement

Partial multi-label learning addresses scenarios where each instance is associated with a set of candidate labels that include both relevant and irrelevant ones. In practical scenarios, such label sets are often simultaneously incomplete and noisy, which severely hampers the ability of models to extract compact and discriminative features. To address these issues, we propose an integrated learning paradigm that simultaneously enhances feature compactness and improves robustness against label noise. Our method constructs a similarity graph through the fuzzy C-means algorithm to capture the intrinsic relationships among instances. The resulting graph enables reliable label propagation, which effectively rectifies incorrect annotations and infers missing labels. In addition, we introduce a feature disentanglement mechanism that isolates reliable label-related feature representations from spurious ones introduced by noisy supervision. By integrating feature learning and label refinement into a joint optimization process, the proposed approach achieves a synergistic improvement in both representation quality and label reliability. Extensive theoretical analysis and empirical studies on multiple benchmark datasets demonstrate that our framework consistently outperforms state-of-the-art methods in terms of accuracy, stability and robustness to annotation noise.