期刊
INFORMATION SCIENCES
卷 563, 期 -, 页码 23-39出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2021.02.008
关键词
Soft subspace clustering; Multi-objective optimization; Composite kernels; Evolutionary algorithm
资金
- National Natural Science Foundation of China (NSFC) [71731001, 71843011]
A novel multi-objective soft subspace clustering model is proposed in this study, which simultaneously optimizes three clustering criteria, measures the distance between data points in a composite kernel space, and optimizes the weight of base kernels using a multi-objective evolutionary algorithm to address the problems in conventional algorithms.
Conventional subspace clustering algorithms group the data samples by optimizing the objective function which aggregates different clustering criteria using the linear combination. However, the performance is sensitive to the user-defined coefficients. Besides, the widely used Euclidean distance metric falls short of handling the linear indivisible problems. Some composite kernel metrics are proposed to overcome this drawback, but it is still difficult to determine the proper weight of base kernels. To address these problems, a novel multi-objective soft subspace clustering model is proposed. The novel model simultaneously optimizes three clustering criteria without setting coefficients. The distance between data points is measured in a composite kernel space. The weight of base kernels is optimized by a multi-objective evolutionary algorithm. A decomposition-based local search strategy is developed to enhance the performance of the proposed algorithm. The experimental results indicate that the proposed algorithm can achieve better solutions. (c) 2021 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据