2023/10/15 by Yuxiu Lin, Lin, Yuxiu, Hui Liu +6
Computer Science · Mathematics · Social Sciences · #Advanced Computing and Algorithms #Algorithm #Artificial intelligence #Bottleneck #Cluster analysis #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Constraint (computer-aided design) #FOS: Computer and information sciences #Face and Expression Recognition #Information bottleneck method #Machine Learning (cs.LG) #Mathematics #Parameterized complexity #Pattern recognition (psychology) #Representation (politics) #Subspace topology #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.2310.09718
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/10/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent multi-view subspace clustering achieves impressive results utilizing deep networks, where the self-expressive correlation is typically modeled by a fully connected (FC) layer. However, they still suffer from two limitations. i) The parameter scale of the FC layer is quadratic to sample numbers, resulting in high time and memory costs that significantly degrade their feasibility in large-scale datasets. ii) It is under-explored to extract a unified representation that simultaneously satisfies minimal sufficiency and discriminability. To this end, we propose a novel deep framework, termed Efficient and Effective deep Multi-View Subspace Clustering (E2MVSC). Instead of a parameterized FC layer, we design a Relation-Metric Net that decouples network parameter scale from sample numbers for greater computational efficiency. Most importantly, the proposed method devises a multi-type auto-encoder to explicitly decouple consistent, complementary, and superfluous information from every view, which is supervised by a soft clustering assignment similarity constraint. Following information bottleneck theory and the maximal coding rate reduction principle, a sufficient yet minimal unified representation can be obtained, as well as pursuing intra-cluster aggregation and inter-cluster separability within it. Extensive experiments show that E2MVSC yields comparable results to existing methods and achieves state-of-the-art performance in various types of multi-view datasets.