%0 Conference Paper %1 Zhang09parallelCommunity %A Zhang, Yuzhou %A Wang, Jianyong %A Wang, Yi %A Zhou, Lizhu %B KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining %C New York, NY, USA %D 2009 %I ACM %K 09 Zhang clustering community detection graph parallel %P 997--1006 %R http://doi.acm.org/10.1145/1557019.1557127 %T Parallel community detection on large networks with propinquity dynamics %U http://portal.acm.org/citation.cfm?id=1557019.1557127 %X Graphs or networks can be used to model complex systems. Detecting community structures from large network data is a classic and challenging task. In this paper, we propose a novel community detection algorithm, which utilizes a dynamic process by contradicting the network topology and the topology-based propinquity, where the propinquity is a measure of the probability for a pair of nodes involved in a coherent community structure. Through several rounds of mutual reinforcement between topology and propinquity, the community structures are expected to naturally emerge. The overlapping vertices shared between communities can also be easily identified by an additional simple postprocessing. To achieve better efficiency, the propinquity is incrementally calculated. We implement the algorithm on a vertex-oriented bulk synchronous parallel(BSP) model so that the mining load can be distributed on thousands of machines. We obtained interesting experimental results on several real network data. %@ 978-1-60558-495-9

@inproceedings{Zhang09parallelCommunity, abstract = {Graphs or networks can be used to model complex systems. Detecting community structures from large network data is a classic and challenging task. In this paper, we propose a novel community detection algorithm, which utilizes a dynamic process by contradicting the network topology and the topology-based propinquity, where the propinquity is a measure of the probability for a pair of nodes involved in a coherent community structure. Through several rounds of mutual reinforcement between topology and propinquity, the community structures are expected to naturally emerge. The overlapping vertices shared between communities can also be easily identified by an additional simple postprocessing. To achieve better efficiency, the propinquity is incrementally calculated. We implement the algorithm on a vertex-oriented bulk synchronous parallel(BSP) model so that the mining load can be distributed on thousands of machines. We obtained interesting experimental results on several real network data.}, added-at = {2010-01-14T20:21:50.000+0100}, address = {New York, NY, USA}, author = {Zhang, Yuzhou and Wang, Jianyong and Wang, Yi and Zhou, Lizhu}, biburl = {https://www.bibsonomy.org/bibtex/2b0faa1a66fa8c4087d185e8233bafba4/lee_peck}, booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining}, description = {Parallel community detection on large networks with propinquity dynamics}, doi = {http://doi.acm.org/10.1145/1557019.1557127}, interhash = {12f43ad8e99fb3b3cc59af340ad462ac}, intrahash = {b0faa1a66fa8c4087d185e8233bafba4}, isbn = {978-1-60558-495-9}, keywords = {09 Zhang clustering community detection graph parallel}, location = {Paris, France}, pages = {997--1006}, publisher = {ACM}, timestamp = {2010-01-14T20:21:50.000+0100}, title = {Parallel community detection on large networks with propinquity dynamics}, url = {http://portal.acm.org/citation.cfm?id=1557019.1557127}, year = 2009 }