Approximation algorithms for classification problems with pairwise relationships
Top Cited Papers
- 1 September 2002
- journal article
- Published by Association for Computing Machinery (ACM) in Journal of the ACM
- Vol. 49 (5), 616-639
- https://doi.org/10.1145/585265.585268
Abstract
In a traditional classification problem, we wish to assign one of k labels (or classes) to each of n objects , in a way that is consistent with some observed data that we have about the problem. An active line of research in this area is concerned with classification when one has information about pairwise relationships among the objects to be classified; this issue is one of the principal motivations for the framework of Markov random fields, and it arises in areas such as image processing, biometry, and document analysis. In its most basic form, this style of analysis seeks to find a classification that optimizes a combinatorial function consisting of assignment costs ---based on the individual choice of label we make for each object---and separation costs ---based on the pair of choices we make for two "related" objects.We formulate a general classification problem of this type, the metric labeling problem ; we show that it contains as special cases a number of standard classification frameworks, including several arising from the theory of Markov random fields. From the perspective of combinatorial optimization, our problem can be viewed as a substantial generalization of the multiway cut problem, and equivalent to a type of uncapacitated quadratic assignment problem .We provide the first nontrivial polynomial-time approximation algorithms for a general family of classification problems of this type. Our main result is an O (log k log log k )-approximation algorithm for the metric labeling problem, with respect to an arbitrary metric on a set of k labels, and an arbitrary weighted graph of relationships on a set of objects. For the special case in which the labels are endowed with the uniform metric ---all distances are the same---our methods provide a 2-approximation algorithm.Keywords
This publication has 8 references indexed in Scilit:
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Minimum 0-Extensions of Graph MetricsEuropean Journal of Combinatorics, 1998
- Markov Random Field Modeling in Computer VisionPublished by Springer Science and Business Media LLC ,1995
- The Complexity of Multiterminal CutsSIAM Journal on Computing, 1994
- Evolutionary trees: An integer multicommodity max-flow-min-cut theoremAdvances in Applied Mathematics, 1992
- Markov Random Fields for Image Modelling & AnalysisPublished by Springer Science and Business Media LLC ,1986
- Markov Random Fields and Their ApplicationsContemporary Mathematics, 1980
- Some generalized order-disorder transformationsMathematical Proceedings of the Cambridge Philosophical Society, 1952