Abstract
As most ‘real-world’ data is structured, research in kernel methods has begun investigating kernels for various kinds of structured data. One of the most widely used tools for modeling structured data are graphs. An interesting and important challenge is thus to investigate kernels on instances that are represented by graphs. So far, only very specific graphs such as trees and strings have been considered.
This paper investigates kernels on labeled directed graphs with general structure. It is shown that computing a strictly positive definite graph kernel is at least as hard as solving the graph isomorphism problem. It is also shown that computing an inner product in a feature space indexed by all possible graphs, where each feature counts the number of subgraphs isomorphic to that graph, is NP-hard. On the other hand, inner products in an alternative feature space, based on walks in the graph, can be computed in polynomial time. Such kernels are defined in this paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Haussler, D. (ed.) Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, July 1992, pp. 144–152. ACM Press, New York (1992)
Collins, M., Duffy, N.: Convolution kernels for natural language. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems, Cambridge, MA, vol. 14. MIT Press, Cambridge (2002)
Diestel, R.: Graph Theory. Springer, Heidelberg (2000)
Gärtner, T.: Exponential and geometric kernels for graphs. In: NIPS Workshop on Unreal Data: Principles of Modeling Nonvectorial Data (2002)
Gärtner, T.: Kernel-based multi-relational data mining. In: SIGKDD Explorations (2003) (to appear)
Gärtner, T., Driessens, K., Ramon, J.: Graph kernels and gaussian processes for relational reinforcement learning. In: Proceedings of the 13th International Conference on Inductive Logic Programming (2003) (submitted)
Gray, R.: Probability, Random Processes, and Ergodic Properties. Springer, Heidelberg (1987)
Imrich, W., Klavžar, S.: Product Graphs: Structure and Recognition. John Wiley, Chichester (2000)
Kashima, H., Inokuchi, A.: Kernels for graph classification. In: ICDM Workshop on Active Mining (2002)
Kashima, H., Tsuda, K., Inokuchi, A.: Marginalized kernels between labeled graphs. In: Proceedings of the 20th International Conference on Machine Learning (2003) (to appear)
Köbler, J., Schöning, U., Töran, J.: The Graph Isomorphism Problem: Its Structural Complexity. Progress in Theoretical Computer Science. Birkhäuser, Basel (1993)
Kondor, R.I., Lafferty, J.: Diffusion kernels on graphs and other discrete input spaces. In: Sammut, C., Hoffmann, A. (eds.) Proceedings of the 19th International Conference on Machine Learning, pp. 315–322. Morgan Kaufmann, San Francisco (2002)
Korte, B., Vygen, J.: Combinatorial Optimization: Theory and Algorithms. Springer, Heidelberg (2002)
Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text lassification using string kernels. Journal of Machine Learning Research 2, 419–444 (2002)
Schölkopf, B., Smola, A.J.: Learning with Kernels. The MIT Press, Cambridge (2002)
Skena, S.: The Algorithm Design Manual. Springer, Heidelberg (1997)
Watkins, C.: Kernels from matching operations. Technical report, Department of Computer Science, Royal Holloway, University of London (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gärtner, T., Flach, P., Wrobel, S. (2003). On Graph Kernels: Hardness Results and Efficient Alternatives. In: Schölkopf, B., Warmuth, M.K. (eds) Learning Theory and Kernel Machines. Lecture Notes in Computer Science(), vol 2777. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45167-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-45167-9_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40720-1
Online ISBN: 978-3-540-45167-9
eBook Packages: Springer Book Archive