Robust clustering with sparse corruption via ℓ2,1, ℓ1 norm constraint and Laplacian regularization

作者：

Highlights：

• Propose a joint optimization framework for clustering.

• Utilize ℓ2,1 and ℓ1 to alleviate the influence of outliers and noises.

• Prove algorithm convergence from theoretical and practical aspects.

• Experimentation on three different types of real datasets.

摘要

•Propose a joint optimization framework for clustering.•Utilize ℓ2,1 and ℓ1 to alleviate the influence of outliers and noises.•Prove algorithm convergence from theoretical and practical aspects.•Experimentation on three different types of real datasets.

论文关键词：Laplacian regularization,Rotation invariance property of ℓ2, 1norm,Noise and outliers,Robust clustering,Alternating direction method of multipliers (ADMM)

论文评审过程：Received 12 January 2020, Revised 12 July 2021, Accepted 30 July 2021, Available online 8 August 2021, Version of Record 11 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115704