CUED Publications database

Distributed flow algorithms for scalable similarity visualization

Quadrianto, N and Schuurmans, D and Smola, AJ (2010) Distributed flow algorithms for scalable similarity visualization. Proceedings - IEEE International Conference on Data Mining, ICDM. pp. 1220-1227. ISSN 1550-4786

Full text not available from this repository.

Abstract

We describe simple yet scalable and distributed algorithms for solving the maximum flow problem and its minimum cost flow variant, motivated by problems of interest in objects similarity visualization. We formulate the fundamental problem as a convex-concave saddle point problem. We then show that this problem can be efficiently solved by a first order method or by exploiting faster quasi-Newton steps. Our proposed approach costs at most O(|ε|) per iteration for a graph with |ε| edges. Further, the number of required iterations can be shown to be independent of number of edges for the first order approximation method. We present experimental results in two applications: mosaic generation and color similarity based image layouting. © 2010 IEEE.

Item Type: Article
Uncontrolled Keywords: Distributed algorithms Flow networks Linear programming Visualization
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:20
Last Modified: 08 Dec 2014 02:27
DOI: 10.1109/ICDMW.2010.120