A Counting-Based Heuristic for ILP-Based Concept Discovery Systems
Concept discovery systems are concerned with learning definitions of a specific relation in terms of other relations provided as background knowledge. Although such systems have a history of more than 20 years and successful applications in various domains, they are still vulnerable to scalability and efficiency issues —mainly due to large search spaces they build. In this study we propose a heuristic to select a target instance that will lead to smaller search space without sacrificing the accuracy. The proposed heuristic is based on counting the occurrences of constants in the target relation. To evaluate the heuristic, it is implemented as an extension to the concept discovery system called C 2 D. The experimental results show that the modified version of C 2 D builds smaller search space and performs better in terms of running time without any decrease in coverage in comparison to the one without extension.
KeywordsInductive Logic Programming Concept Discovery Search Space Counting
Unable to display preview. Download preview PDF.
- 1.Muggleton, S.: Inductive Logic Programming. In: The MIT Encyclopedia of the Cognitive Sciences (MITECS). MIT Press (1999)Google Scholar
- 3.Muggleton, S., Feng, C.: Efficient induction of logic programs. In: Proceedings of the 1st Conference on Algorithmic Learning Theory, pp. 368–381. Springer/Ohmsma (1990)Google Scholar
- 7.Nassif, H., Page, D., Ayvaci, M., Shavlik, J., Burnside, E.S.: Uncovering age-specific invasive and dcis breast cancer rules using inductive logic programming. In: Proceedings of the 1st ACM International Health Informatics Symposium, pp. 76–82. ACM (2010)Google Scholar
- 9.Amini, A., Shrimpton, P.J., Muggleton, S.H., Sternberg, M.J.: A general approach for developing system-specific functions to score protein–ligand docked complexes using support vector inductive logic programming. Proteins: Structure, Function, and Bioinformatics 69(4), 823–831 (2007)CrossRefGoogle Scholar
- 11.Konstantopoulos, S.: A data-parallel version of Aleph. CoRR abs/0708.1527 (2007)Google Scholar
- 12.Mutlu, A., Senkul, P.: Improving hit ratio of ilp-based concept discovery system with memoization. The Computer Journal (2012), doi:10.1093/comjnl/bxs163Google Scholar
- 14.Tausend, B.: Representing biases for inductive logic programming. In: Proceedings of the 7th European Conference on Machine Learning, Catania, Italy, April 6-8, pp. 427–430 (1994)Google Scholar
- 16.Srinivasan, A.: The Aleph Manual (1999), http://www.comlab.ox.ac.uk/activities/machinelearning/Aleph/ (accessed April 06, 2013)
- 17.http://www.cs.utexas.edu/ftp/mooney/forte/ (accessed April 10, 2013)
- 18.Dolšak, B., Bratko, I., Jezernik, A.: Finite element mesh design: An engineering domain for ILP application. In: Proceedings of the 4th International Workshop on Inductive Logic Programming, Bonn, Germany, Gesellschaft für Mathematik und Datenverarbeitung MBH, September 12-14, pp. 305–320 (1994)Google Scholar
- 19.Srinivasan, A., King, R.D., Muggleton, S.H., Sternberg, M.: The predictive toxicology evaluation challenge. In: IJCAI 1997: Proceedings of the 15th International Joint Conference on Artificial Intelligence, pp. 1–6 (1997)Google Scholar