Does Multi-Clause Learning Help in Real-World Applications?

  • Dianhuan Lin
  • Jianzhong Chen
  • Hiroaki Watanabe
  • Stephen H. Muggleton
  • Pooja Jain
  • Michael J. E. Sternberg
  • Charles Baxter
  • Richard A. Currie
  • Stuart J. Dunbar
  • Mark Earll
  • José Domingo Salazar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7207)

Abstract

The ILP system Progol is incomplete in not being able to generalise a single example to multiple clauses. This limitation is referred as single-clause learning (SCL) in this paper. However, according to the Blumer bound, incomplete learners such as Progol can have higher predictive accuracy while use less search than more complete learners. This issue is particularly relevant in real-world problems, in which it is unclear whether the unknown target theory or its approximation is within the hypothesis space of the incomplete learner. This paper uses two real-world applications in systems biology to study whether it is necessary to have complete multi-clause learning (MCL) methods, which is computationally expensive but capable of deriving multi-clause hypotheses that is in the systems level. The experimental results show that in both applications there do exist datasets, in which MCL has significantly higher predictive accuracies than SCL. On the other hand, MCL does not outperform SCL all the time due to the existence of the target hypothesis or its approximations within the hypothesis space of SCL.

Keywords

Integrity Constraint Hypothesis Space Target Theory High Predictive Accuracy System Hypothesis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Occam’s razor. Information Processing Letters 24(6), 377–380 (1987)MathSciNetMATHCrossRefGoogle Scholar
  3. 3.
    Centeno, D.C., Osorio, S., et al.: Malate plays a crucial role in starch metabolism, ripening, and soluble solid content of tomato fruit and affects postharvest softening. Plant Cell 23, 162–184 (2011)CrossRefGoogle Scholar
  4. 4.
    Corapi, D., Russo, A., Lupu, E.: Inductive logic programming as abductive search. In: ICLP 2010 Technical Communications. Springer, Berlin (2010)Google Scholar
  5. 5.
    Waterman, C.L., et al.: An integrated functional genomic study of acute phenobarbital exposure in the rat. BMC Genomics 11(1), 9 (2010)CrossRefGoogle Scholar
  6. 6.
    Fernie, A.R., Carrari, F., Sweetlove, L.J.: Respiratory metabolism: glycolysis, the TCA cycle and mitochondrial electron transport. Current Opinion in Plant Biology 7, 254–261 (2004)CrossRefGoogle Scholar
  7. 7.
    Inoue, K.: Induction as consequence finding. Machine Learning 55, 109–135 (2004)MATHCrossRefGoogle Scholar
  8. 8.
    Inoue, K., Sato, T., Ishihata, M., et al.: Evaluating abductive hypotheses using an EM algorithm on BDDs. In: IJCAI 2009, pp. 810–815 (2009)Google Scholar
  9. 9.
    LycoCyc. Solanum lycopersicum database, http://solcyc.solgenomics.net//LYCO/
  10. 10.
    Muggleton, S.H.: Inverse entailment and Progol. New Generation Computing 13, 245–286 (1995)CrossRefGoogle Scholar
  11. 11.
    Muggleton, S.H., Bryant, C.H.: Theory Completion Using Inverse Entailment. In: Cussens, J., Frisch, A.M. (eds.) ILP 2000. LNCS (LNAI), vol. 1866, pp. 130–146. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  12. 12.
    Muggleton, S.H., Chen, J., Watanabe, H., Dunbar, S.J., Baxter, C., Currie, R., Salazar, J.D., Taubert, J., Sternberg, M.J.E.: Variation of Background Knowledge in an Industrial Application of ILP. In: Frasconi, P., Lisi, F.A. (eds.) ILP 2010. LNCS, vol. 6489, pp. 158–170. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Muggleton, S.H., Lin, D., Tamaddoni-Nezhad, A.: MC-TopLog: Complete Multi-clause Learning Guided by a Top Theory. In: Muggleton, S.H., Tamaddoni-Nezhad, A., Lisi, F.A. (eds.) ILP 2011. LNCS (LNAI), vol. 7207, pp. 239–255. Springer, Heidelberg (2012)Google Scholar
  14. 14.
    Ogata, H., Goto, S., Sato, K., Fujibuchi, W., Bono, H., Kanehisa, M.: KEGG: Kyoto Encyclopedia of Genes and Genomes. Nucl. Acids Res. 27(1), 29–34 (1999)CrossRefGoogle Scholar
  15. 15.
    Ray, O.: Nonmonotonic abductive inductive learning. Journal of Applied Logic 7(3), 329–340 (2009)MathSciNetMATHCrossRefGoogle Scholar
  16. 16.
    Tamaddoni-Nezhad, A., Bohan, D., Raybould, A., Muggleton, S.H.: Machine Learning a Probabilistic Network of Ecological Interactions. In: Muggleton, S.H., Tamaddoni-Nezhad, A., Lisi, F.A. (eds.) ILP 2011. LNCS (LNAI), vol. 7207, pp. 319–333. Springer, Heidelberg (2012)Google Scholar
  17. 17.
    Tamaddoni-Nezhad, A., Chaleil, R., Kakas, A., Muggleton, S.H.: Application of abductive ILP to learning metabolic network inhibition from temporal data. Machine Learning 64, 209–230 (2006)MATHCrossRefGoogle Scholar
  18. 18.
    Valiant, L.: A theory of the learnable. Journal of the ACM 27(11), 1134–1142 (1984)MATHCrossRefGoogle Scholar
  19. 19.
    Yamamoto, A.: Which Hypotheses can be Found with Inverse Entailment? In: Džeroski, S., Lavrač, N. (eds.) ILP 1997. LNCS, vol. 1297, pp. 296–308. Springer, Heidelberg (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Dianhuan Lin
    • 1
  • Jianzhong Chen
    • 1
  • Hiroaki Watanabe
    • 1
  • Stephen H. Muggleton
    • 1
  • Pooja Jain
    • 1
  • Michael J. E. Sternberg
    • 1
  • Charles Baxter
    • 2
  • Richard A. Currie
    • 2
  • Stuart J. Dunbar
    • 2
  • Mark Earll
    • 2
  • José Domingo Salazar
    • 2
  1. 1.Imperial College LondonUK
  2. 2.Syngenta Ltd.UK

Personalised recommendations