Multi-view Feature Extraction based on Dual Contrastive Head

TL;DR

This paper introduces a multi-view feature extraction method that combines sample-level and structural-level contrastive learning, improving discriminative feature extraction in high-dimensional multi-view data.

Contribution

It proposes a dual contrastive head that integrates structural-level contrastive loss with sample-level CL, enhancing feature extraction effectiveness.

Findings

Outperforms existing methods on six real datasets

Theoretical analysis links structural CL with mutual information

Structural CL improves discriminative feature learning

Abstract

Multi-view feature extraction is an efficient approach for alleviating the issue of dimensionality in highdimensional multi-view data. Contrastive learning (CL), which is a popular self-supervised learning method, has recently attracted considerable attention. Most CL-based methods were constructed only from the sample level. In this study, we propose a novel multiview feature extraction method based on dual contrastive head, which introduce structural-level contrastive loss into sample-level CL-based method. Structural-level CL push the potential subspace structures consistent in any two cross views, which assists sample-level CL to extract discriminative features more effectively. Furthermore, it is proven that the relationships between structural-level CL and mutual information and probabilistic intraand inter-scatter, which provides the theoretical support for the excellent performance. Finally, numerical experiments on six real datasets demonstrate the superior performance of the proposed method compared to existing methods.