Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification

TL;DR

This paper introduces a novel framework for incomplete multi-view multi-label classification that factorizes representations into view-consistent and view-specific factors, effectively handling data incompleteness and improving classification performance.

Contribution

The proposed framework uniquely decomposes multi-view representations into independent factors and employs a graph disentangling loss, advancing robustness in incomplete multi-view multi-label classification.

Findings

Outperforms existing methods on five datasets.

Effectively handles incomplete views and labels.

Improves view-consistent and view-specific representation learning.

Abstract

Multi-view multi-label classification (MvMLC) has recently garnered significant research attention due to its wide range of real-world applications. However, incompleteness in views and labels is a common challenge, often resulting from data collection oversights and uncertainties in manual annotation. Furthermore, the task of learning robust multi-view representations that are both view-consistent and view-specific from diverse views still a challenge problem in MvMLC. To address these issues, we propose a novel framework for incomplete multi-view multi-label classification (iMvMLC). Our method factorizes multi-view representations into two independent sets of factors: view-consistent and view-specific, and we correspondingly design a graph disentangling loss to fully reduce redundancy between these representations. Additionally, our framework innovatively decomposes consistent representation learning into three key sub-objectives: (i) how to extract view-shared information across different views, (ii) how to eliminate intra-view redundancy in consistent representations, and (iii) how to preserve task-relevant information. To this end, we design a robust task-relevant consistency learning module that collaboratively learns high-quality consistent representations, leveraging a masked cross-view prediction (MCP) strategy and information theory. Notably, all modules in our framework are developed to function effectively under conditions of incomplete views and labels, making our method adaptable to various multi-view and multi-label datasets. Extensive experiments on five datasets demonstrate that our method outperforms other leading approaches.