skip to main content
research-article

Exact Learning: On the Boundary between Horn and CNF

Authors Info & Claims
Published:11 February 2020Publication History
Skip Abstract Section

Abstract

A major problem in computational learning theory is whether the class of formulas in conjunctive normal form (CNF) is efficiently learnable. Although it is known that this class cannot be polynomially learned using either membership or equivalence queries alone, it is open whether the CNF class can be polynomially learned using both types of queries. One of the most important results concerning a restriction of the CNF class is that propositional Horn formulas are polynomial time learnable in Angluin’s exact learning model with membership and equivalence queries. In this work, we push this boundary and show that the class of multivalued dependency formulas (MVDF), which non-trivially extends propositional Horn, is polynomially learnable from interpretations. We then provide a notion of reduction between learning problems in Angluin’s model, showing that a transformation of the algorithm suffices to efficiently learn multivalued database dependencies from data relations. We also show via reductions that our main result extends well known previous results and allows us to find alternative solutions for them.

References

  1. Dana Angluin. 1987. Learning k-term DNF Formulas Using Queries and Counterexamples. Technical Report. Department of Computer Science, Yale University.Google ScholarGoogle Scholar
  2. Dana Angluin. 1987. Learning regular sets from queries and counterexamples. Inf. Comput. 75, 2 (1987), 87--106.Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Dana Angluin. 1988. Queries and concept learning. Mach. Learn. 2, 4 (1988), 319--342.Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. Dana Angluin. 1990. Negative results for equivalence queries. Mach. Learn. 5 (1990), 121--150.Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. Dana Angluin, Michael Frazier, and Leonard Pitt. 1992. Learning conjunctions of Horn clauses. Mach. Learn. 9 (1992), 147--164.Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. Dana Angluin and Michael Kharitonov. 1995. When won't membership queries help? J. Comput. Syst. Sci. 50, 2 (1995), 336--355.Google ScholarGoogle ScholarDigital LibraryDigital Library
  7. Marta Arias and José L. Balcázar. 2011. Construction and learnability of canonical Horn formulas. Mach. Learn. 85, 3 (2011), 273--297.Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. José L. Balcázar and Jaume Baixeries. 2004. Characterizations of multivalued dependencies and related expressions. In Proceedings of the 7th International Conference on Discovery Science (DS’04). 306--313.Google ScholarGoogle Scholar
  9. N. H. Bshouty. 1995. Exact learning boolean functions via the monotone theory. Inf. Comput. 123, 1 (1995), 146--153.Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. Edgar F. Codd. 1970. A relational model of data for large shared data banks. Commun. ACM 13, 6 (1970), 377--387.Google ScholarGoogle ScholarCross RefCross Ref
  11. Ronald Fagin. 1977. Functional dependencies in a relational database and propositional logic. IBM J. Res. Dev. 21, 6 (1977), 534--544.Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. Ronald Fagin. 1977. Multivalued dependencies and a new normal form for relational databases. ACM Trans. Database Syst. 2 (1977), 262--278.Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. Peter A. Flach and Iztok Savnik. 1999. Database dependency discovery: A machine learning approach. AI Commun. 12, 3 (1999), 139--160.Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. Michael Frazier and Leonard Pitt. 1993. Learning from entailment: An application to propositional Horn sentences. In Proceedings of the 10th International Conference on Machine Learning. 120--127.Google ScholarGoogle ScholarCross RefCross Ref
  15. Michael Duane Frazier. 1994. Matters Horn and Other Features in the Computational Learning Theory Landscape: The Notion of Membership. Ph.D. Dissertation. University of Illinois Urbana. 36--37.Google ScholarGoogle Scholar
  16. Lisa Hellerstein and Vijay Raghavan. 2002. Exact learning of DNF formulas using DNF hypotheses. In Proceedings of the 34th Annual ACM Symposium on Theory of Computing (STOC’02). ACM, New York, NY, 465--473.Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. Montserrat Hermo and Ana Ozaki. 2015. Exact learning of multivalued dependencies. In Proceedings of the 26th International Conference on Algorithmic Learning Theory. Springer, 73--88.Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. Montserrat Hermo and Ana Ozaki. 2018. Exact learning of multivalued dependency formulas. Theor. Comput. Sci. 716, 15 (2018), 4--14. DOI:https://doi.org/10.1016/j.tcs.2017.11.018Google ScholarGoogle ScholarCross RefCross Ref
  19. Ykä Huhtala, Juha Kärkkäinen, Pasi Porkka, and Hannu Toivonen. 1998. Efficient discovery of functional and approximate dependencies using partitions. In Proceedings of the 14th International Conference on Data Engineering 1998. IEEE, 392--401.Google ScholarGoogle ScholarCross RefCross Ref
  20. Martti Kantola, Heikki Mannila, Kari-Jouko Räihä, and Harri Siirtola. 1992. Discovering functional and inclusion dependencies in relational databases. Int. J. Intell. Syst. 7, 7 (1992), 591--607.Google ScholarGoogle ScholarCross RefCross Ref
  21. Michael Kearns, Ming Li, Leonard Pitt, and Leslie Valiant. 1987. On the learnability of boolean formulae. In Proceedings of the 19th Annual ACM Symposium on Theory of Computing. 285--295.Google ScholarGoogle ScholarDigital LibraryDigital Library
  22. Michael J. Kearns and Umesh Vazirani. 1994. An Introduction to Computational Learning Theory. MIT Press. 155--156.Google ScholarGoogle Scholar
  23. Boris Konev, Ana Ozaki, and Frank Wolter. 2016. A model for learning description logic ontologies based on exact learning. In Proceedings of the Conference on Artificial Intelligence (AAAI’16). AAAI Press, 1008--1015.Google ScholarGoogle Scholar
  24. Víctor Lavín. 2011. On learning multivalued dependencies with queries. Theor. Comput. Sci. 412, 22 (2011), 2331--2339.Google ScholarGoogle ScholarDigital LibraryDigital Library
  25. Víctor Lavín. 2015. Learning an extension of the class of functional dependencies with queries. New Generat. Comput. 33, 3 (2015), 319--340.Google ScholarGoogle ScholarCross RefCross Ref
  26. Víctor Lavín and Montserrat Hermo. 2011. Negative results on learning multivalued dependencies with queries. Inform. Process. Lett. 111, 19 (2011), 968--972.Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. Nick Littlestone. 1988. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Mach. Learn. 2, 4 (April 1988), 285--318.Google ScholarGoogle ScholarCross RefCross Ref
  28. Heikki Mannila and Kari-Jouko Räihä. 1994. Algorithms for inferring functional dependencies from relations. Data Knowl. Eng. 12, 1 (1994), 83--99.Google ScholarGoogle ScholarDigital LibraryDigital Library
  29. Krishnan Pillaipakkamnatt and Vijay Raghavan. 1995. Read-twice DNF formulas are properly learnable. Information and Computation 122, 2 (1995), 236--267.Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. Leonard Pitt and Manfred K. Warmuth. 1988. Reductions among prediction problems: On the difficulty of predicting automata. In Proceedings of the 3rd Annual Structure in Complexity Theory Conference, 1988. 60--69.Google ScholarGoogle Scholar
  31. Víctor Lavín Puente. 2015. Learning sets of antecedent-restricted functional and multivalued dependencies with queries. Theory Comput. Syst. (2015), 1--17.Google ScholarGoogle Scholar
  32. Yehoshua Sagiv, Claude Delobel, D. Scott Parker, Jr., and Ronald Fagin. 1981. An equivalence between relational database dependencies and a fragment of propositional logic. J. ACM 28, 3 (1981), 435--453.Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. Leslie G. Valiant. 1984. A theory of the learnable. Commun. ACM 27, 11 (1984), 1134--1142.Google ScholarGoogle ScholarDigital LibraryDigital Library
  34. Osamu Watanabe. 1994. A framework for polynomial-time query learnability. Theory Comput. Syst. 27, 3 (1994), 211--229.Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Exact Learning: On the Boundary between Horn and CNF

          Recommendations

          Comments

          Login options

          Check if you have access through your login credentials or your institution to get full access on this article.

          Sign in

          Full Access

          • Published in

            cover image ACM Transactions on Computation Theory
            ACM Transactions on Computation Theory  Volume 12, Issue 1
            March 2020
            199 pages
            ISSN:1942-3454
            EISSN:1942-3462
            DOI:10.1145/3376904
            Issue’s Table of Contents

            Copyright © 2020 ACM

            Publisher

            Association for Computing Machinery

            New York, NY, United States

            Publication History

            • Published: 11 February 2020
            • Accepted: 1 September 2019
            • Received: 1 June 2018
            Published in toct Volume 12, Issue 1

            Permissions

            Request permissions about this article.

            Request Permissions

            Check for updates

            Qualifiers

            • research-article
            • Research
            • Refereed

          PDF Format

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format .

          View HTML Format
          About Cookies On This Site

          We use cookies to ensure that we give you the best experience on our website.

          Learn more

          Got it!