Multi-view graph clustering methods have been widely concerned due to the ability of dealing with arbitrarily shaped datasets. However, many methods with higher time and space complexity make them challenging to deal with large-scale datasets. Besides, many fuzzy clustering methods needs additional regularization terms or hyper-parameters to obtain the membership matrix or avoid trivial solutions, which weakens the model generalization ability. Furthermore, inconsistent clustering labels can arise when there are significant discrepancies between views, making it challenging to effectively leverage the complementary information from different views. To this end, we propose Tensorized Label Learning based Fast Fuzzy Clustering (TLLFFC). Specifically, we design a novel balanced regularization term to reduce pressure of tuning regularization parameters for fuzzy clustering. The label transmission strategy with the anchor graph makes TLLFFC suitable for large-scale datasets. Moreover, incorporating the Schatten p-norm regularization on the label matrices can effectively unearth the complementary information distributed among views, thereby align the labels across views more consistently. Extensive experiments verify the superiority of TLLFFC.

Large-scale multi-view clustering for image data has achieved impressive clustering performance and efficiency. However, most methods lack interpretability in clustering and do not fully consider the complementarity of distributions between different views. To address these problems, we introduce Multi-View Clustering with Transition Probabilities Learning (MVC-TPL). Specifically, we construct an anchor graph factorization model from the perspective of transition probabilities, while simultaneously learning transition probability matrices from samples to clusters and from anchor points to clusters, serving as soft label matrices for samples and anchor points, respectively. This model enables one-step label acquisition and provides the model with a sound probability interpretation. Moreover, since the clusters of samples and anchor points should be consistent across all views, we employ Schatten p-norm regularization on the two matrices, effectively mining the complementary information distributed among the views, thereby aligning the labels across views more consistently. Comprehensive testing on four small-scale datasets and three large-scale datasets confirms the effectiveness of this model.