SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering

Ruimeng Liu (China University of Geosciences (Wuhan)) · Xin Zou (The Hong Kong University of Science and Technology) · Chang Tang (China University of Geosciences) · Xiao Zheng (Hubei University of Technology) · Xingchen Hu (National University of Defense Technology) · Kun Sun (China University of Geosciences Wuhan) · Xinwang Liu (National University of Defense Technology)
adaptive sparse autoencodersattention mechanismscorrelation-informed sample reweightingcross-view sparsity variationsdata-level sparsityencoding discrepanciesentropy-matching lossfeature distribution alignmentglobal featureslate fusionmulti-view clusteringsemantic heterogeneitystate-of-the-art clustering performanceview-level dynamic fusionview-specific features

Existing multi-view clustering methods employ various strategies to address data-level sparsity and view-level dynamic fusion. However, we identify a critical yet overlooked issue: varying sparsity across views. Cross-view sparsity variations lead to encoding discrepancies, heightening sample-level semantic heterogeneity and making view-level dynamic weighting inappropriate. To tackle these challenges, we propose Adaptive Sparse Autoencoders for Multi-View Clustering (SparseMVC), a framework with three key modules. Initially, the sparse autoencoder probes the sparsity of each view and adaptively adjusts encoding formats via an entropy-matching loss term, mitigating cross-view inconsistencies. Subsequently, the correlation-informed sample reweighting module employs attention mechanisms to assign weights by capturing correlations between early-fused global and view-specific features, reducing encoding discrepancies and balancing contributions. Furthermore, the cross-view distribution alignment module aligns feature distributions during the late fusion stage, accommodating datasets with an arbitrary number of views. Extensive experiments demonstrate that SparseMVC achieves state-of-the-art clustering performance. Our framework advances the field by extending sparsity handling from the data-level to view-level and mitigating the adverse effects of encoding discrepancies through sample-level dynamic weighting. The source code is publicly available at https://github.com/cleste-pome/SparseMVC.