TY - GEN
T1 - Spectral active clustering via purification of the K-Nearest neighbor graph
AU - Xiong, Caiming
AU - Johnson, David
AU - Corso, Jason
PY - 2012
Y1 - 2012
N2 - Spectral clustering is widely used in data mining, machine learning and pattern recognition. There have been some recent developments in adding pairwise constraints as side information to enforce top-down structure into the clustering results. However, most of these algorithms are "passive" in the sense that the side information is provided beforehand. In this paper, we present a spectral active clustering method that actively selects pairwise constraints based on a novel no tion of node uncertainty rather than pair uncertainty. In our approach, the constraints are used to drive a purification process on the k-nearest neighbor graph - edges are rem oved from the graph ba sed on the constraints - that ultimately leads to an improved, constraint-satisfied clustering. We have evaluated our framework on three datasets (UCI, gene and image sets) in the context of baseline and state of the art methods and find the proposed algorithm to be superiorly effective.
AB - Spectral clustering is widely used in data mining, machine learning and pattern recognition. There have been some recent developments in adding pairwise constraints as side information to enforce top-down structure into the clustering results. However, most of these algorithms are "passive" in the sense that the side information is provided beforehand. In this paper, we present a spectral active clustering method that actively selects pairwise constraints based on a novel no tion of node uncertainty rather than pair uncertainty. In our approach, the constraints are used to drive a purification process on the k-nearest neighbor graph - edges are rem oved from the graph ba sed on the constraints - that ultimately leads to an improved, constraint-satisfied clustering. We have evaluated our framework on three datasets (UCI, gene and image sets) in the context of baseline and state of the art methods and find the proposed algorithm to be superiorly effective.
KW - Active clustering
KW - KNN Graph
KW - Purification
KW - Spectral clustering
UR - http://www.scopus.com/inward/record.url?scp=84887449224&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84887449224&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84887449224
SN - 9789728939694
T3 - Proceedings of the IADIS International Conference Intelligent Systems and Agents 2012, ISA 2012, IADIS European Conference on Data Mining 2012, ECDM 2012
SP - 133
EP - 141
BT - Proceedings of the IADIS International Conference Intelligent Systems and Agents 2012, ISA 2012, IADIS European Conference on Data Mining 2012, ECDM 2012
T2 - IADIS International Conference Intelligent Systems and Agents 2012, ISA 2012, IADIS European Conference on Data Mining 2012, ECDM 2012, Part of the IADIS Multi Conference on Computer Science and Information Systems 2012, MCCSIS 2012
Y2 - 21 July 2012 through 23 July 2012
ER -