Edit distance-based kernel functions for structural pattern classification

  • Authors:
  • Michel Neuhaus;Horst Bunke

  • Affiliations:
  • Department of Computer Science, University of Bern, Neubrückstrasse 10, CH-3012 Bern, Switzerland;Department of Computer Science, University of Bern, Neubrückstrasse 10, CH-3012 Bern, Switzerland

  • Venue:
  • Pattern Recognition
  • Year:
  • 2006

Quantified Score

Hi-index 0.01

Visualization

Abstract

A common approach in structural pattern classification is to define a dissimilarity measure on patterns and apply a distance-based nearest-neighbor classifier. In this paper, we introduce an alternative method for classification using kernel functions based on edit distance. The proposed approach is applicable to both string and graph representations of patterns. By means of the kernel functions introduced in this paper, string and graph classification can be performed in an implicit vector space using powerful statistical algorithms. The validity of the kernel method cannot be established for edit distance in general. However, by evaluating theoretical criteria we show that the kernel functions are nevertheless suitable for classification, and experiments on various string and graph datasets clearly demonstrate that nearest-neighbor classifiers can be outperformed by support vector machines using the proposed kernel functions.