A Domain Adaptive Density Clustering Algorithm for Data With Varying Density Distribution
Authors:
- 19 November 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 33 (6) , 2310-2321
Abstract
As one type of efficient unsupervised learning methods, clustering algorithms have been widely used in data mining and knowledge discovery with noticeable advantages. However, clustering algorithms based on density peak have limited clustering effect on data with varying density distribution (VDD), equilibrium distribution (ED), and multiple domain-density maximums (MDDM), leading to the problems of sparse cluster loss and cluster fragmentation. To address these problems, we propose a Domain-Adaptive Density Clustering (DADC) algorithm, which consists of three steps: domain-adaptive density measurement, cluster center self-identification, and cluster self-ensemble. For data with VDD features, clusters in sparse regions are often neglected by using uniform density peak thresholds, which results in the loss of sparse clusters. We define a domain-adaptive density measurement method based on $K$ -Nearest Neighbors (KNN) to adaptively detect the density peaks of different density regions. We treat each data point and its KNN neighborhood as a subgroup to better reflect its density distribution in a domain view. In addition, for data with ED or MDDM features, a large number of density peaks with similar values can be identified, which results in cluster fragmentation. We propose a cluster center self-identification and cluster self-ensemble method to automatically extract the initial cluster centers and merge the fragmented clusters. Experimental results demonstrate that compared with other comparative algorithms, the proposed DADC algorithm can obtain more reasonable clustering results on data with VDD, ED and MDDM features. Benefitting from a few parameter requirement and non-iterative nature, DADC achieves low computational complexity and is suitable for large-scale data clustering.
Keywords
All Related Versions
Funding Information
- International Postdoctoral Exchange Fellowship Program (20180024)
- National Science Foundation (III-1526499, III-1763325, III-1909323, CNS-1930941)
This publication has 23 references indexed in Scilit:
- Robust clustering by detecting density peaks and assigning points based on fuzzy weighted K-nearest neighborsInformation Sciences, 2016
- Study on density peaks clustering based on k-nearest neighbors and principal component analysisKnowledge-Based Systems, 2016
- Automatic Clustering via Outward Statistical Testing on Density MetricsIEEE Transactions on Knowledge and Data Engineering, 2016
- Trust Evaluation in Online Social Networks Using Generalized Network FlowIEEE Transactions on Computers, 2015
- A Framework for Hierarchical Ensemble ClusteringACM Transactions on Knowledge Discovery From Data, 2014
- Clustering by fast search and find of density peaksScience, 2014
- A Survey of Clustering Algorithms for Big Data: Taxonomy and Empirical AnalysisIEEE Transactions on Emerging Topics in Computing, 2014
- epiCProceedings of the VLDB Endowment, 2014
- Nonparametric Bayesian Clustering Ensembles2010
- OPTICS1999