A biclustering approach based on factor graphs and the max-sum algorithm. (February 2017)

• Record Type: Journal Article
• Authors: Denitto, M.; Farinelli, A.; Figueiredo, M.A.T.; Bicego, M.
• Is Part Of: Pattern recognition. Volume 62(2017:Feb.)
• Page Start: 114
• Page End: 124
• Publication Date: 2017-02
• Subjects: Biclustering -- Coclustering -- Factor graphs -- Max-sum -- Expression data; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2016.08.033
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Biclustering represents an intrinsically complex problem, where the aim is to perform a simultaneous row- and column-clustering of a given data matrix. Some recent approaches model this problem using factor graphs, so to exploit their ability to open the door to efficient optimization approaches for well designed function decompositions. However, while such models provide promising results, they do not scale to data matrices of reasonable size. In this paper, we take a step towards addressing this issue, by proposing a novel approach to biclustering based on factor graphs, which yields high quality solutions and scales more favorably than previous methods. Specifically, we cast biclustering as the sequential search for a single bicluster, and propose a binary and compact factor graph that can be solved efficiently using the max-sum algorithm. The proposed approach has been tested and compared with state-of-the-art methods on four datasets (two synthetic and two real world data), providing encouraging results with respect both to previous approaches based on factor graphs and to other state-of-the-art methods. Abstract : Highlights: A novel compact Factor Graph for Biclustering is proposed. The approach exploits Max-Sum and the message passing scheme for the optimization. Closed form message updates have been derived (derivation included in the paper). The proposed method favorably compares with current state-of-the-art.