Affinity Propagation Clustering Using Path Based Similarity
AbstractClustering is a fundamental task in data mining. Affinity propagation clustering (APC) is an effective and efficient clustering technique that has been applied in various domains. APC iteratively propagates information between affinity samples, updates the responsibility matrix and availability matrix, and employs these matrices to choose cluster centers (or exemplars) of respective clusters. However, since it mainly uses negative Euclidean distance between exemplars and samples as the similarity between them, it is difficult to identify clusters with complex structure. Therefore, the performance of APC deteriorates on samples distributed with complex structure. To mitigate this problem, we propose an improved APC based on a path-based similarity (APC-PS). APC-PS firstly utilizes negative Euclidean distance to find exemplars of clusters. Then, it employs the path-based similarity to measure the similarity between exemplars and samples, and to explore the underlying structure of clusters. Next, it assigns non-exemplar samples to their respective clusters via that similarity. Our empirical study on synthetic and UCI datasets shows that the proposed APC-PS significantly outperforms original APC and other related approaches. View Full-Text
Share & Cite This Article
Jiang, Y.; Liao, Y.; Yu, G. Affinity Propagation Clustering Using Path Based Similarity. Algorithms 2016, 9, 46.
Jiang Y, Liao Y, Yu G. Affinity Propagation Clustering Using Path Based Similarity. Algorithms. 2016; 9(3):46.Chicago/Turabian Style
Jiang, Yuan; Liao, Yuliang; Yu, Guoxian. 2016. "Affinity Propagation Clustering Using Path Based Similarity." Algorithms 9, no. 3: 46.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.