Replication on Affinity Propagation: Clustering by Passing Messages Between Data Points
Zhe Zhao · 2007
In this project, I choose the paper, Clustering by Passing Messages Between Data Points [1], published in Science 2007, as the work to replicate. In [1], a new clustering algorithm named Affinity Propagation is proposed. In my report, three research hypothesizes in this paper that are related to the performance, evaluation and scalability of the algorithm are studied. I implement the algorithm and conduct extensive experiments to test these three research hypothesizes. Based on the results, some of the hypothesizes are accepted and some are rejected. I also try to use Affinity Propagation in the task of clustering tweets as the extension of this project.