ACM Computing Surveys (CSUR)
Random walk with restart: fast solutions and applications
Knowledge and Information Systems
Generating diverse and representative image search results for landmarks
Proceedings of the 17th international conference on World Wide Web
Finding image exemplars using fast sparse affinity propagation
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Proceedings of the 18th international conference on World wide web
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Laplacian Discriminant Projection Based on Affinity Propagation
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Clustering to find exemplar terms for keyphrase extraction
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Efficient ad-hoc search for personalized PageRank
Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data
Hi-index | 0.00 |
Affinity Propagation is a state-of-the-art clustering method recently proposed by Frey and Dueck. It has been successfully applied to broad areas of computer science research because it has much better clustering performance than traditional clustering methods such as k-means. In order to obtain high quality sets of clusters, the original Affinity Propagation algorithm iteratively exchanges real-valued messages between all pairs of data points until convergence. However, this algorithm does not scale for large datasets because it requires quadratic CPU time in the number of data points to compute the messages. This paper proposes an efficient Affinity Propagation algorithm that guarantees the same clustering result as the original algorithm after convergence. The heart of our approach is (1) to prune unnecessary message exchanges in the iterations and (2) to compute the convergence values of prunedmessages after the iterations to determine clusters. Experimental evaluations on several different datasets demonstrate the effectiveness of our algorithm.