Feature-Label Modal Alignment for Robust Partial Multi-Label Learning
2026-04-10 • Machine Learning
Machine Learning
AI summaryⓘ
The authors address a type of learning where each example has multiple possible labels, but some labels might be wrong. They propose a method called PML-MA that treats features and labels like two different but connected views, aligning them to correct noisy labels. Their method first cleans up the labels using a special decomposition, then matches features and labels in a shared space while preserving relationships among data points. They also use a way to learn multiple category prototypes that helps handle instances belonging to several classes at once. Tests show their approach works better than existing methods in accuracy and handling label noise.
Partial Multi-Label LearningNoisy LabelsFeature-Label AlignmentLow-Rank Orthogonal DecompositionPseudo-LabelingMulti-Label ClassificationPrototype LearningNeighborhood Structure PreservationMulti-Modal LearningLabel Noise Robustness
Authors
Yu Chen, Weijun Lv, Yue Huang, Xiaozhao Fang, Jie Wen, Yong Xu, Guanbin Li
Abstract
In partial multi-label learning (PML), each instance is associated with a set of candidate labels containing both ground-truth and noisy labels. The presence of noisy labels disrupts the correspondence between features and labels, degrading classification performance. To address this challenge, we propose a novel PML method based on feature-label modal alignment (PML-MA), which treats features and labels as two complementary modalities and restores their consistency through systematic alignment. Specifically, PML-MA first employs low-rank orthogonal decomposition to generate pseudo-labels that approximate the true label distribution by filtering noisy labels. It then aligns features and pseudo-labels through both global projection into a common subspace and local preservation of neighborhood structures. Finally, a multi-peak class prototype learning mechanism leverages the multi-label nature where instances simultaneously belong to multiple categories, using pseudo-labels as soft membership weights to enhance discriminability. By integrating modal alignment with prototype-guided refinement, PML-MA ensures pseudo-labels better reflect the true distribution while maintaining robustness against label noise. Extensive experiments on both real-world and synthetic datasets demonstrate that PML-MA significantly outperforms state-of-the-art methods, achieving superior classification accuracy and noise robustness.