关键词: 不完整性, 多视图聚类, 图数据挖掘, 缺失视图, 多视图学习

Abstract: Multi-view clustering has recently been a hot topic in graph data mining. However, due to the limitations of data collection technology or human factors, multi-view data often has the problem of missing views or samples. Incompleteness of multi-views is one of the major challenges facing multi-view clustering. In order to better understand the development of incomplete multi-view clustering in recent years, a comprehensive review is of great theoretical and practical importance. Firstly, the missing types of incomplete multi-view data were summarized and analyzed. Secondly, four types of incomplete multi-view clustering methods, based on multiple kernel learning, matrix factorization learning, deep learning, and graph learning were compared, and the technical characteristics and differences among the methods were analyzed. Thirdly, from the perspectives of dataset types, the number of views and categories, and application fields, 22 public incomplete multi-view datasets were conducted. Then, the evaluation metrics were outlined, and the performance of existing incomplete multi-view clustering methods on homogeneous and heterogeneous datasets were evaluated. Finally, the existing problems, future research directions, and existing application fields of incomplete multi-view clustering were discussed.

Key words: incompleteness, multi-view clustering, graph data mining, missing view, multi-view learning