On Graph Kernels: Hardness Results and Efficient Alternatives
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.
KeywordsFeature Space Adjacency Matrix Product Graph Hamiltonian Path Transition Graph
Unable to display preview. Download preview PDF.
- 2.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)Google Scholar
- 4.Gärtner, T.: Exponential and geometric kernels for graphs. In: NIPS Workshop on Unreal Data: Principles of Modeling Nonvectorial Data (2002)Google Scholar
- 5.Gärtner, T.: Kernel-based multi-relational data mining. In: SIGKDD Explorations (2003) (to appear)Google Scholar
- 6.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)Google Scholar
- 7.Gray, R.: Probability, Random Processes, and Ergodic Properties. Springer, Heidelberg (1987)Google Scholar
- 9.Kashima, H., Inokuchi, A.: Kernels for graph classification. In: ICDM Workshop on Active Mining (2002)Google Scholar
- 10.Kashima, H., Tsuda, K., Inokuchi, A.: Marginalized kernels between labeled graphs. In: Proceedings of the 20th International Conference on Machine Learning (2003) (to appear)Google Scholar
- 11.Köbler, J., Schöning, U., Töran, J.: The Graph Isomorphism Problem: Its Structural Complexity. Progress in Theoretical Computer Science. Birkhäuser, Basel (1993)Google Scholar
- 12.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)Google Scholar
- 15.Schölkopf, B., Smola, A.J.: Learning with Kernels. The MIT Press, Cambridge (2002)Google Scholar
- 16.Skena, S.: The Algorithm Design Manual. Springer, Heidelberg (1997)Google Scholar
- 17.Watkins, C.: Kernels from matching operations. Technical report, Department of Computer Science, Royal Holloway, University of London (1999)Google Scholar