Machine Learning

, Volume 70, Issue 2–3, pp 121–133 | Cite as

QG/GA: a stochastic search for Progol

  • Stephen Muggleton
  • Alireza Tamaddoni-Nezhad


Most search techniques within ILP require the evaluation of a large number of inconsistent clauses. However, acceptable clauses typically need to be consistent, and are only found at the “fringe” of the search space. A search approach is presented, based on a novel algorithm called QG (Quick Generalization). QG carries out a random-restart stochastic bottom-up search which efficiently generates a consistent clause on the fringe of the refinement graph search without needing to explore the graph in detail. We use a Genetic Algorithm (GA) to evolve and re-combine clauses generated by QG. In this QG/GA setting, QG is used to seed a population of clauses processed by the GA. Experiments with QG/GA indicate that this approach can be more efficient than standard refinement-graph searches, while generating similar or better solutions.


Stochastic search Refinement Genetic Algorithms 


  1. Botta, M., Giordana, A., Saitta, L., & Sebag, M. (2003). Relational learning as search in a critical region. Journal of Machine Learning Research, 4, 431–463. CrossRefMathSciNetGoogle Scholar
  2. Haussler, D., Kearns, M., & Shapire, R. (1994). Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension. Machine Learning, 14(1), 83–113. MATHGoogle Scholar
  3. Inoue, K. (2001). Induction, abduction and consequence-finding. In C. Rouveirol & M. Sebag (Eds.), Lecture notes in artificial intelligence : Vol. 2157. Proceedings of the eleventh international workshop on inductive logic programming (ILP01) (pp. 65–79). Berlin: Springer. CrossRefGoogle Scholar
  4. Ito, K., & Yamamoto, A. (1998). Finding hypotheses from examples by computing the least generalization of bottom clauses. In S. Arikawa & H. Motoda (Eds.), Lecture notes in artificial intelligence : Vol. 1532. Proceedings of discovery science ’98 (pp. 303–314). Berlin: Springer. CrossRefGoogle Scholar
  5. King, R., Muggleton, S., Srinivasan, A., & Sternberg, M. (1996). Structure-activity relationships derived by machine learning: the use of atoms and their bond connectives to predict mutagenicity by inductive logic programming. Proceedings of the National Academy of Sciences, 93, 438–442. CrossRefGoogle Scholar
  6. Kovacic, M. (1994). Stochastic inductive logic programming. PhD thesis, University of Ljubljana, Ljubljana, Slovenia. Google Scholar
  7. Mitchell, T. (1997). Machine learning. New York: McGraw-Hill. MATHGoogle Scholar
  8. Muggleton, S. (1995). Inverse entailment and Progol. New Generation Computing, 13, 245–286. CrossRefGoogle Scholar
  9. Muggleton, S. H., & Feng, C. (1990). Efficient induction of logic programs. In Proceedings of the first conference on algorithmic learning theory (pp. 368–381). Tokyo: Ohmsha. Google Scholar
  10. Paes, A., Zelezny, F., Zaverucha, G., Page, D., & Srinivasan, A. (2006). ILP through Propositionalization and Stochastic k-term DNF learning. In S. Muggleton, R. Otero, & A. Tamaddoni-Nezhad (Eds.), Proceedings of the 16th international conference on inductive logic programming (pp. 379–393). Berlin: Springer. Google Scholar
  11. Page, D., & Srinivasan, A. (2003). ILP: a short look back and a longer look forward. Journal of Machine Learning Research, 4, 415–430. CrossRefGoogle Scholar
  12. Ray, O., Broda, K., & Russo, A. (2003). Hybrid abductive inductive learning: a generalization of Progol. In Lecture notes in artificial intelligence : Vol. 2835. 13th international conference on inductive logic programming (pp. 311–328). Berlin: Springer. Google Scholar
  13. Ruckert, U., & Kramer, S. (2003). Stochastic local search in k-term DNF learning. In Proceedings of the 20th international conference on machine learning (pp. 648–655). Google Scholar
  14. Sebag, M., & Rouveirol, C. (2000). Resource-bounded relational reasoning: Induction and deduction through stochastic matching. Machine Learning, 38, 43–65. CrossRefGoogle Scholar
  15. Srinivasan, A. (2000). A study of two probabilistic methods for searching large spaces with ILP (Technical Report PRG-TR-16-00). Oxford University Computing Laboratory, Oxford. Google Scholar
  16. Srinivasan, A. (2005). Five problems in five areas for five years. In S. Kramer & B. Pfahringer (Eds.), Lecture notes in artificial intelligence : Vol. 3625. Proceedings of the 15th international conference on inductive logic programming (p. 424). Berlin: Springer. Google Scholar
  17. Tamaddoni-Nezhad, A., & Muggleton, S. H. (2000). Searching the subsumption lattice by a genetic algorithm. In J. Cussens & A. Frisch (Eds.), Proceedings of the 10th international conference on inductive logic programming (pp. 243–252). Berlin: Springer. CrossRefGoogle Scholar
  18. Tamaddoni-Nezhad, A., & Muggleton, S. H. (2002). A genetic algorithms approach to ILP. In Proceedings of the 12th international conference on inductive logic programming (pp. 285–300). Berlin: Springer. Google Scholar
  19. Zelezny, F., Srinivasan, A., & Page, D. (2004). A Monte Carlo study of randomised restarted search in ILP. In Lecture notes in artificial intelligence : Vol. 3194. Proceedings of the 14th international conference on inductive logic programming (pp. 341–358). Berlin: Springer. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Department of ComputingImperial College LondonLondonUK

Personalised recommendations