Structure regularized consensus dynamic anchor graph learning for incomplete multi-view clustering.

Abstract

Dynamic anchor graph-based incomplete multi-view clustering (IMVC) algorithms have garnered extensive research attention in recent years owing to their relatively low time complexity. However, these algorithms suffer from two limitations. First, most of the existing methods disregard the structural information of the original feature spaces. Second, nearly all the current approaches emphasize the importance of each view while overlooking the weights of each feature. To address these issues, we propose an algorithm named SRCDAGL-IMC. Specifically, we use the structural information of all the views as regularization terms to constrain the relationships between different pairs in the consensus anchor graph. Moreover, we add coefficients to each sample to measure their individual importance in their own view, and we simultaneously recover the missing features. Thus, the learning of the consensus anchor graph, and the recovery of the missing features, mutually promote each other. We also propose an effective alternating optimization method. Experiments on six public datasets show that our algorithm outperforms the state-of-the-art matrix factorization-based incomplete multi-view algorithms in terms of accuracy, normalized mutual information, purity. Our code is publicly available on https://github.com/BingHuAhpu/SRCDAGL-IMC.