Learning Similarity Matrix from Constraints of Relational Neighbors

Masayuki Okabe (Toyohashi University of Technology)
Seiji Yamada (NII/Sokendai)

We developed a method of learning similarity matrix from pairwise constraints assumed used under the situation such as interactive clustering, where we can expect little user feedback. With the small number of pairwise constraints used, our method attempts to use additional constraints induced by the affinity relationship between constrained data and their neighbors. The similarity matrix is learned by solving an optimization problem formalized as semidefinite programming. Additional constraints are used as complementary in the optimization problem. Results of experiments confirmed the effectiveness of our proposed method in several clustering

Constraints propagation.

Publications

• Masayuki Okabe and Seiji Yamada: Learning Similarity Matrix from Constraints of Relational Neighbors, Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.14, No.4, pp. 402-407 (May. 2010)
• Masayuki Okabe and Seiji Yamada: Clustering with Constrained Similarity Learning, In Proceedings of the International Workshop on Intelligent Web Interaction 2009 (IWI 2009), Milan, Italy, pp.30-33 (Sep. 2009)