Multi-View Clustering Via Mixed Embedding Approximation

This paper tackles multi-view clustering via proposing a novel mixed embedding approximation (MEA) method. Formally, we aim to learn a uniform orthogonal embedding based on the orthogonal pre-embeddings of each view. At first, we hope that the uniform embedding can reconstruct the affinity graph of each view. To improve the representation of learnt embedding, we perform an embedding approximation on Grass-mann manifold which is famous on subspace analysis. To perform the difference of views, a hidden weights learning module is provided. Moreover, we propose an iterative algorithm to solve the proposed MEA method and provide rigorously convergence analysis. Extensive experiments demonstrate the superiorities of the proposed method.