Feature-Label Modal Alignment for Robust Partial Multi-Label Learning

2026-04-10

AI Summary

This work addresses the challenge of inaccurate feature-label associations in partial multi-label learning caused by noisy candidate labels. To mitigate this issue, the authors propose a feature-label modality alignment framework that treats features and labels as complementary modalities. The method generates reliable pseudo-labels via low-rank orthogonal decomposition and aligns the two modalities under constraints that preserve both global subspace projection and local neighborhood structure. Furthermore, it incorporates multi-peak class prototypes and a soft membership weighting mechanism to enhance model discriminability and robustness to label noise. Experimental results demonstrate that the proposed approach significantly outperforms existing methods on both real-world and synthetic datasets, achieving notable improvements in classification accuracy and noise tolerance.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• partial multi-label learning
• label noise
• feature-label alignment
• noisy labels
• multi-label classification

Innovation

• modal alignment
• partial multi-label learning
• low-rank orthogonal decomposition
• prototype learning
• label noise robustness