Mutual Calibration Network for Multi-View Clustering

Multi-view clustering, which uses information from multiple views to partition data into distinct clusters, has garnered significant attention. Existing MLP-based and GCN-based algorithms primarily focus on enhancing performance by extracting node attribute and graph structure features, and then integrating them for clustering. However, features extracted by MLP and GCN may differ in quality due to the high sparsity and noise in multi-view data. Directly integrating these features can lead to feature contamination. To address this issue, we propose a novel mutual calibration network for multi-view clustering (McMVC). Specifically, the attribute and structural features from multi-view data are integrated separately using the attention fusion module. A classifier is then employed to obtain high-confidence pseudo-labels for these fused features. We design a Cluster-level Mutual Calibration (CLMC) module that uses the pseudo-labels to mutually calibrate view features while maintaining compact cluster structures. During training, the attribute and structural features are not directly integrated to avoid feature contamination but are jointly optimized by reliable class information. Concurrently, we construct a Centroid-level Contrastive Calibration (CLCC) module to map view features into their inner centroid space and learn more discriminative centroid representations. Our approach outperforms state-of-the-art methods in multi-view data clustering, as demonstrated by extensive experiments on six real-world benchmark datasets. The source code is available at https://github.com/YuangXiao/ McMVC.