Improving evolutionary constrained clustering using Active Learning

作者：

Highlights：

• Four novel Active Learning strategies to FIECE-EM.

• Three of the proposed strategies outperform COBRAS, a state-of-the-art algorithm.

• Experiments on 14 datasets suggest that LUC is the best among the proposed strategies.

摘要

•Four novel Active Learning strategies to FIECE-EM.•Three of the proposed strategies outperform COBRAS, a state-of-the-art algorithm.•Experiments on 14 datasets suggest that LUC is the best among the proposed strategies.

论文关键词：Active Learning,Constrained clustering,Semi-supervised learning,Evolutionary algorithms

论文评审过程：Received 20 April 2020, Revised 3 September 2020, Accepted 4 September 2020, Available online 21 September 2020, Version of Record 22 September 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106452