Incomplete Multi-view Multi-label Classification via a Dual-level Contrastive Learning Framework

TL;DR

This paper introduces a dual-level contrastive learning framework for incomplete multi-view multi-label classification, effectively disentangling view-specific and consistent information to improve classification accuracy in real-world scenarios.

Contribution

It proposes a novel dual-level contrastive learning approach with a decoupling module for better handling incomplete multi-view multi-label data, outperforming existing methods.

Findings

Achieves more stable and superior classification performance on benchmark datasets.

Effectively disentangles view-specific and consistent information.

Demonstrates robustness in incomplete multi-view multi-label scenarios.

Abstract

Recently, multi-view and multi-label classification have become significant domains for comprehensive data analysis and exploration. However, incompleteness both in views and labels is still a real-world scenario for multi-view multi-label classification. In this paper, we seek to focus on double missing multi-view multi-label classification tasks and propose our dual-level contrastive learning framework to solve this issue. Different from the existing works, which couple consistent information and view-specific information in the same feature space, we decouple the two heterogeneous properties into different spaces and employ contrastive learning theory to fully disentangle the two properties. Specifically, our method first introduces a two-channel decoupling module that contains a shared representation and a view-proprietary representation to effectively extract consistency and complementarity information across all views. Second, to efficiently filter out high-quality consistent information from multi-view representations, two consistency objectives based on contrastive learning are conducted on the high-level features and the semantic labels, respectively. Extensive experiments on several widely used benchmark datasets demonstrate that the proposed method has more stable and superior classification performance.