Abstract. The problems of finding alternative clusterings and avoiding bias have gained popularity over the last years. In this paper we put the focus on the quality of these alter...
— Recent work has revealed a close connection between certain information theoretic divergence measures and properties of Mercer kernel feature spaces. Specifically, it has been...
We propose preprocessing spectral clustering with b-matching to remove spurious edges in the adjacency graph prior to clustering. B-matching is a generalization of traditional maxi...
ct We introduce a new family of spectral partitioning methods. Edge separators of a graph are produced by iteratively reweighting the edges until the graph disconnects into the pre...
Sense Induction is the process of identifying the word sense given its context, often treated as a clustering task. This paper explores the use of spectral cluster method which in...