Semantically Consistent Multi-view Representation Learning

TL;DR

This paper introduces SCMRL, a novel unsupervised multi-view learning method that leverages semantic consensus to improve unified feature representations, outperforming existing algorithms.

Contribution

The paper proposes a new framework that incorporates semantic consensus information into unsupervised multi-view learning, enhancing feature alignment and representation quality.

Findings

SCMRL outperforms state-of-the-art methods in experiments.

Semantic consensus effectively guides feature learning.

Contrastive learning aligns semantic labels across views.

Abstract

In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from multiple views in an unsupervised manner. Existing UMRL methods mainly concentrate on the learning process in the feature space while ignoring the valuable semantic information hidden in different views. To address this issue, we propose a novel Semantically Consistent Multi-view Representation Learning (SCMRL), which makes efforts to excavate underlying multi-view semantic consensus information and utilize the information to guide the unified feature representation learning. Specifically, SCMRL consists of a within-view reconstruction module and a unified feature representation learning module, which are elegantly integrated by the contrastive learning strategy to simultaneously align semantic labels of both view-specific feature representations and the learned unified feature representation. In this way, the consensus information in the semantic space can be effectively exploited to constrain the learning process of unified feature representation. Compared with several state-of-the-art algorithms, extensive experiments demonstrate its superiority.