Outer-Points shaver: Robust graph-based clustering via node cutting

作者：

Highlights：

• A new graph-based clustering method using node cutting was proposed.

• We present theoretical results that guarantee the robustness in selecting nodes.

• The optimal cluster number can be determined by adjusting a sparsity parameter.

• Comparison studies show that the proposed method outperformed existing methods.

摘要

•A new graph-based clustering method using node cutting was proposed.•We present theoretical results that guarantee the robustness in selecting nodes.•The optimal cluster number can be determined by adjusting a sparsity parameter.•Comparison studies show that the proposed method outperformed existing methods.

论文关键词：Graph-based clustering,Unsupervised learning,Spectral clustering,Pseudo-density reconstruction,Node cutting

论文评审过程：Received 4 September 2018, Revised 30 May 2019, Accepted 13 August 2019, Available online 14 August 2019, Version of Record 19 August 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107001