A review of related density peaks clustering approaches

Density peaks clustering (DPC) is a succinct and efficient algorithm to discover the structure of datasets, and it has been used in a number of domains. However, applying DPC to real-world tasks faces two main challenges: how to estimate the appropriate local density in datasets with different density distributions, and how to robustly forms clusters. Substantial researches make efforts to improve DPC from the aspects of these two challenges so as to result in promising clustering results. In this study, at first, we comprehensively review the different types of local density estimation methods and cluster assignment strategies in DPC-related works, then briefly introduce the application of DPC. At last, we discuss potential future research directions of the DPC algorithm.