Entropy regularization for unsupervised clustering with adaptive neighbors
作者：
Highlights：
• The maximized entropy term with clear prediction meaning under simplex is introduced to avoid two trivial solutions obtained from primal clustering model on neighbors and pure pursuit for entropy maximization, respectively.
• The Laplacian rank constraint with ℓ0-norm is developed to dynamically obtain sparse similarity matrix with exact c connected components, which avoids extra discretization process in classical SC.
• ℓ0-norm constraint assigns fused neighbors for each sample, accelerates the spectral analysis, and assists rank constraint to discover c connected components more accurately.
• A novel monotonic function optimization method is proposed to tackle the ℓ0-norm constraint with fixed pseudo-label matrix, which elegantly reveals the consistence between graph sparsity and neighbor assignment.
摘要
•The maximized entropy term with clear prediction meaning under simplex is introduced to avoid two trivial solutions obtained from primal clustering model on neighbors and pure pursuit for entropy maximization, respectively.•The Laplacian rank constraint with ℓ0-norm is developed to dynamically obtain sparse similarity matrix with exact c connected components, which avoids extra discretization process in classical SC.•ℓ0-norm constraint assigns fused neighbors for each sample, accelerates the spectral analysis, and assists rank constraint to discover c connected components more accurately.•A novel monotonic function optimization method is proposed to tackle the ℓ0-norm constraint with fixed pseudo-label matrix, which elegantly reveals the consistence between graph sparsity and neighbor assignment.
论文关键词：Unsupervised clustering,Similarity matrix,Entropy regularization,Trivial similarity distribution,Laplacian rank constraint,Adaptive neighbors
论文评审过程：Received 23 April 2021, Revised 28 October 2021, Accepted 29 December 2021, Available online 4 January 2022, Version of Record 10 January 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108517
