Correlation clustering Export

@misc{citeulike:1221045, abstract = {We consider the following clustering problem: we have a complete graph on n vertices (items), where each edge (u; v) is labeled either + or depending on whether u and v have been deemed to be similar or different. The goal is to produce a partition of the vertices (a clustering) that agrees as much as possible with the edge labels. That is, we want a clustering that maximizes the number of + edges within clusters, plus the number of edges between clusters (equivalently, minimizes the number of disagreements: the number of edges inside clusters plus the number of + edges between clusters). This formulation is motivated from a document clustering problem in which one has a pairwise similarity function f learned from past data, and the goal is to partition the current set of documents in a way that correlates with f as much as possible; it can also be viewed as a kind of {"}agnostic learning{"} problem.}, author = {Bansal, N. and Blum, A. and Chawla, S.}, citeulike-article-id = {1221045}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3857}, journal = {Machine Learning}, keywords = {clustering, graph, signed\_graph}, month = {July}, number = {1-3}, pages = {89--113}, posted-at = {2008-11-04 06:36:19}, priority = {0}, publisher = {Springer}, title = {Correlation clustering}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3857}, volume = {56}, year = {2004} }

TY - GEN ID - citeulike:1221045 L3 - citeulike-article-id:1221045 N2 - We consider the following clustering problem: we have a complete graph on n vertices (items), where each edge (u; v) is labeled either + or depending on whether u and v have been deemed to be similar or different. The goal is to produce a partition of the vertices (a clustering) that agrees as much as possible with the edge labels. That is, we want a clustering that maximizes the number of + edges within clusters, plus the number of edges between clusters (equivalently, minimizes the number of disagreements: the number of edges inside clusters plus the number of + edges between clusters). This formulation is motivated from a document clustering problem in which one has a pairwise similarity function f learned from past data, and the goal is to partition the current set of documents in a way that correlates with f as much as possible; it can also be viewed as a kind of {"}agnostic learning{"} problem. IS - 1-3 JF - Machine Learning EP - 113 TI - Correlation clustering PB - Springer VL - 56 SP - 89 KW - clustering KW - graph KW - signed_graph AU - Bansal, N AU - Blum, A AU - Chawla, S PY - 2004/07// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3857 ER -