Multi-view MERA Subspace Clustering

TL;DR

This paper introduces a novel multi-scale entanglement renormalization ansatz (MERA) based tensor network approach for multi-view subspace clustering, improving representation power and scalability for large datasets.

Contribution

It is the first to apply MERA tensor networks to multi-view clustering, enhancing inter/intra-view information capture and scalability with a new low-rank MERA model.

Findings

MERA-MSC outperforms existing algorithms on multiple datasets and metrics.

The scalable sMERA-MVC method is effective for large-scale multi-view data.

The proposed methods are validated with publicly available code.

Abstract

Tensor-based multi-view subspace clustering (MSC) can capture high-order correlation in the self-representation tensor. Current tensor decompositions for MSC suffer from highly unbalanced unfolding matrices or rotation sensitivity, failing to fully explore inter/intra-view information. Using the advanced tensor network, namely, multi-scale entanglement renormalization ansatz (MERA), we propose a low-rank MERA based MSC (MERA-MSC) algorithm, where MERA factorizes a tensor into contractions of one top core factor and the rest orthogonal/semi-orthogonal factors. Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor. The alternating direction method of multipliers is adopted to solve the optimization model. Experimental results on five multi-view datasets demonstrate MERA-MSC has superiority against the compared algorithms on six evaluation metrics. Furthermore, we extend MERA-MSC by incorporating anchor learning to develop a scalable low-rank MERA based multi-view clustering method (sMREA-MVC). The effectiveness and efficiency of sMERA-MVC have been validated on three large-scale multi-view datasets. To our knowledge, this is the first work to introduce MERA to the multi-view clustering topic. The codes of MERA-MSC and sMERA-MVC are publicly available at https://github.com/longzhen520/MERA-MSC.