Robust Late Fusion on Multi-View Clustering

Abstract

Multi-view clustering, which seeks a partition of the data in multiple views that often provide complementary information to each other, has received considerable attention in recent years. In real life clustering problems, the data in each view may have considerable noise. However, existing clustering methods blindly combine the information from multi-view data with possibly considerable noise, which often degrades their performance. In this paper, we developed RMC, a method for robust multi-view spectral clustering, which explicitly handles the possible noise in the multi-view input data and recovers a shared similarity matrix via low-rank and sparse decomposition. To solve the optimization problem of RMC, we proposed a procedure based on the ALM scheme. Extensive experiments in real world datasets for multi-view clustering show that RMC has encouraging performance gain over the state-of-the-arts.