Auto-weighted Multi-view Subspace Clustering with Consistency Learning

Abstract

Multi-view subspace clustering (MSC) has received widespread attention due to its ability to efficiently exploit consensus and diversity information from multiple perspectives. However, existing methods focus more on inter-view diversity and ignore the consistent associations and higher-order features among views under different perspectives. To solve the above problems, an auto-weighted MSC with consistency learning (AWMSCC) is proposed. Specifically, this method first integrates the shared features of all coefficient matrices in a three-factor decomposition to construct a new shared consistency matrix. Then, by using the tensor low-rank constraint, the coefficient matrices and the shared consistency matrix are stacked into a third-order tensor to achieve effective propagation of inter-view consistency information. Finally, the appropriate weights are adaptively assigned to all matrix information to obtain a high-quality affinity matrix. Experimental results on four benchmark datasets show that AWMSCC outperforms seven other advanced clustering algorithms in terms of performance.