Graph regularized low-rank representation for submodule clustering

作者：

Highlights：

• We present a new unified framework for submodule clustering.

• The approach explicitly considers the manifold structure of data.

• A nonlinear extension is proposed for manifold clustering using kernel methods.

• Experimental results demonstrate the effectiveness of the proposed methods.

摘要

•We present a new unified framework for submodule clustering.•The approach explicitly considers the manifold structure of data.•A nonlinear extension is proposed for manifold clustering using kernel methods.•Experimental results demonstrate the effectiveness of the proposed methods.

论文关键词：Clustering,Kernel methods,Manifold regularization,Submodule clustering,Tensor nuclear norm,Union of free submodules

论文评审过程：Received 5 April 2019, Revised 4 November 2019, Accepted 27 November 2019, Available online 28 November 2019, Version of Record 6 December 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107145