A weighted multi-view clustering via sparse graph learning

Abstract Multi-view clustering considers the diversity of di erent views and fuses these views to produce a more accurate and robust partition than single-view clustering. It is a key problem of multi-view clustering research to allocate each view reasonably based on its contribution value. In this paper, we propose a weighted multi-view clustering model via sparse graph learning to cope with allocation of di erent views. The mainly proposed the idea is to assign di erent view weights instead of equal view weights to learn a highquality shared similarity matrix for multi-view clustering. In our new proposed method, it can consider the clustering capacity heterogeneity of di erent views in fusion by assigning a weight for each view so that the each view special features are fully excavated, and improve the performance of multi-view clustering. As we all know, the high time cost is the main challenge of multi-view clustering algorithm. A signi cant advantage of our proposed algorithm is that it can directly obtain the model solution without the general Singular Value Decomposition or Eigenvalue Decomposition. And thus, the time consumption of the algorithm is reduced e ectively. Meanwhile, our model is proposed based on sparse graph, so that the outliers and noise in each view data are well handled and the robust of the algorithm is e ectively guaranteed. In addition, our proposed method can directly obtained the cluster indicators by imposing low rank constraints without any post-processing operations. Finally, numerous experimental results are conducted on four widely used benchmark datasets, and show that the performance of our algorithm is quite satisfactory.