The complexity of learning minor closed graph classes

  • Carlos Domingo
  • John Shawe-Taylor
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 997)


The paper considers the problem of learning classes of graphs closed under taking minors. It is shown that any such class can be properly learned in polynomial time using membership and equivalence queries. The representation of the class is in terms of a set of minimal excluded minors (obstruction set). Moreover, a negative result for learning such classes using only equivalence queries is also provided, after introducing a notion of reducibility among query learning problems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. Angluin. Queries and Concept Learning, Machine Learning, 2 (1988) 319–342.Google Scholar
  2. 2.
    D. Angluin. Negative results for equivalence queries. Machine Learning, 5 (1990) 121–150.Google Scholar
  3. 3.
    L. Hellerstein, and M. Karpinski. Learning read-once formulas with membership queries. Proc. of the 2nd COLT, San Mateo, CA, (1989), 162–174.Google Scholar
  4. 4.
    P. Auer, N. Cesa-Bianchi. On-Line Learning with Malicious Noise and the Closure Algorithm Proc. of the 5th International Workshop on Algorithmic Learning Theory, LNAI, 872 (1994) 229–247. To appear in Annals of AI and Mathematics Google Scholar
  5. 5.
    H.L. Bodlaender. A Tourist Guide through Treewidth, Acta Cybernetica, 11 (1993).Google Scholar
  6. 6.
    C. Domingo. Improved Fingerprints, Unpublished Manuscript, (1994).Google Scholar
  7. 7.
    R. Gavaldà. On the Power of Equivalence Queries. Proc. of the First European Conference in Computational Learning Theory, (1993), 193–203.Google Scholar
  8. 8.
    M.R. Fellows and M.A. Langston. Exploiting RS-posets: Constructive algorithms from nonconstructive tools. Preprint, Feb. 1989.Google Scholar
  9. 9.
    K. Makino and T. Ibaraki. A Fast and Simple Algorithm for Identifying 2-Monotonic Positive Boolean Functions Technical Report of IEICE, COMP94-46 (1994) 11–20.Google Scholar
  10. 10.
    L. Pitt and M. K. Warmuth, Prediction-Preserving Reducibility Journal of Computer Science, 41, (1990), 430–467.Google Scholar
  11. 11.
    N. Robertson and P.D. Seymour. Graph minors. I. Excluding a forest. J. Comb. Theory Series B, 35 (1983) 39–61.Google Scholar
  12. 12.
    N. Robertson and P.D. Seymour. Graph minors. III. Planar tree-width. J. Comb. Theory Series B, 36 (1984) 49–64.CrossRefGoogle Scholar
  13. 13.
    N. Robertson and P.D. Seymour. Graph minors. II. Algorithmic aspects of tree-width. J. Algorithms, 7 (1986) 309–322.CrossRefGoogle Scholar
  14. 14.
    N. Robertson and P.D. Seymour. Graph minors. V. Excluding a planar graph. J. Comb. Theory Series B, 41 (1986) 92–114.Google Scholar
  15. 15.
    N. Robertson and P.D. Seymour. Graph minors. IV. Tree-width and well-quasiordering. J. Comb. Theory Series B, 48 (1990) 227–254.Google Scholar
  16. 16.
    John Shawe-Taylor, Carlos Domingo, Hans Bodlaender and James Abello, Learning Minor Closed Graph Classes with Membership and Equivalence Queries, Neuro COLT Technical Report NC-TR-94-014, 1994.Google Scholar
  17. 17.
    O. Watanabe. A formal study of learning via queries. Lecture Notes in Computer Science 443: Proceedings of the 17th ICALP,M.S.Paterson, ed., Springer-Verlag, (1990) 139–152.Google Scholar
  18. 18.
    O. Watanabe. A framework for polynomial time query learnability Math. Systems Theory, 27 (1994) 211–229.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Carlos Domingo
    • 1
  • John Shawe-Taylor
    • 2
  1. 1.Dept. of Computer ScienceTokyo Institute of TechnologyTokyoJapan
  2. 2.Dept of Computer Science, Royal HollowayUniversity of LondonEghamEngland

Personalised recommendations