Engineering graph clustering: Models and experimental evaluation Export

@article{citeulike:4073313, abstract = {A promising approach to graph clustering is based on the intuitive notion of intracluster density versus intercluster sparsity. As for the weighted case, clusters should accumulate lots of weight, in contrast to their connection to the remaining graph, which should be light. While both formalizations and algorithms focusing on particular aspects of this rather vague concept have been proposed, no conclusive argument on their appropriateness has been given. In order to deepen the understanding of particular concepts, including both quality assessment as well as designing new algorithms, we conducted an experimental evaluation of graph-clustering approaches. By combining proved techniques from graph partitioning and geometric clustering, we also introduce a new approach that compares favorably.}, address = {New York, NY, USA}, author = {Brandes, Ulrik and Gaertler, Marco and Wagner, Dorothea}, citeulike-article-id = {4073313}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1227161.1227162}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1227161.1227162}, doi = {10.1145/1227161.1227162}, issn = {1084-6654}, journal = {J. Exp. Algorithmics}, keywords = {algorithms, kdd, sys\_performance}, pages = {1--26}, posted-at = {2009-02-20 08:46:41}, priority = {2}, publisher = {ACM}, title = {Engineering graph clustering: Models and experimental evaluation}, url = {http://dx.doi.org/10.1145/1227161.1227162}, volume = {12}, year = {2008} }

TY - JOUR ID - citeulike:4073313 L3 - citeulike-article-id:4073313 N2 - A promising approach to graph clustering is based on the intuitive notion of intracluster density versus intercluster sparsity. As for the weighted case, clusters should accumulate lots of weight, in contrast to their connection to the remaining graph, which should be light. While both formalizations and algorithms focusing on particular aspects of this rather vague concept have been proposed, no conclusive argument on their appropriateness has been given. In order to deepen the understanding of particular concepts, including both quality assessment as well as designing new algorithms, we conducted an experimental evaluation of graph-clustering approaches. By combining proved techniques from graph partitioning and geometric clustering, we also introduce a new approach that compares favorably. JF - J. Exp. Algorithmics SN - 1084-6654 AD - New York, NY, USA EP - 26 TI - Engineering graph clustering: Models and experimental evaluation PB - ACM VL - 12 SP - 1 KW - algorithms KW - kdd KW - sys_performance AU - Brandes, Ulrik AU - Gaertler, Marco AU - Wagner, Dorothea PY - 2008/// UR - http://dx.doi.org/10.1145/1227161.1227162 ER -