A memory efficient graph kernel

Giovanni Martino, Nicolo Navarin, Alessandro Sperduti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper, we show how learning models generated by a recently introduced state-of-the-art kernel for graphs can be optimized from the point of view of memory occupancy. After a brief description of the kernel, we introduce a novel representation of the explicit feature space of the kernel based on an hash function which allows to reduce the amount of memory needed both during the training phase and to represent the final learned model. Subsequently, we study the application of a feature selection strategy based on the F-score to further reduce the number of features in the final model. On two representative datasets involving binary classification of chemical graphs, we show that it is actually possible to sensibly reduce memory occupancy (up to one order of magnitude) for the final model with a moderate loss in classification performance.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD
Duration: 10 Jun 201215 Jun 2012

Other

Other2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
CityBrisbane, QLD
Period10/6/1215/6/12

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Martino, G., Navarin, N., & Sperduti, A. (2012). A memory efficient graph kernel. In Proceedings of the International Joint Conference on Neural Networks [6252831] https://doi.org/10.1109/IJCNN.2012.6252831