Learning Implications from Data and from Queries

  • Sergei ObiedkovEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11511)


In this paper, we consider computational problems related to finding implications in an explicitly given formal context or via queries to an oracle. We are concerned with two types of problems: enumerating implications (or association rules) and finding a single implication satisfying certain conditions. We present complexity results for some of these problems and leave others open. The paper is not meant as a comprehensive survey, but rather as a subjective selection of interesting problems.


Formal concept analysis Learning with queries Attribute exploration Implications Association rules 


  1. 1.
    Adaricheva, K., Nation, J.: Discovery of the D-basis in binary tables based on hypergraph dualization. Theor. Comput. Sci. 658, 307–315 (2017)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Angluin, D.: Queries and concept learning. Mach. Learn. 2(4), 319–342 (1988)MathSciNetGoogle Scholar
  3. 3.
    Angluin, D., Frazier, M., Pitt, L.: Learning conjunctions of Horn clauses. Mach. Learn. 9(2–3), 147–164 (1992)zbMATHGoogle Scholar
  4. 4.
    Angluin, D., Kriis, M., Sloan, R.H., Turán, G.: Malicious omissions and errors in answers to membership queries. Mach. Learn. 28(2), 211–255 (1997)CrossRefGoogle Scholar
  5. 5.
    Angluin, D., Slonim, D.K.: Randomly fallible teachers: learning monotone DNF with an incomplete membership oracle. Mach. Learn. 14(1), 7–26 (1994)zbMATHGoogle Scholar
  6. 6.
    Arias, M., Balcázar, J.L.: Construction and learnability of canonical Horn formulas. Mach. Learn. 85(3), 273–297 (2011)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Arias, M., Balcázar, J.L., Tîrnăucă, C.: Learning definite Horn formulas from closure queries. Theor. Comput. Sci. 658(Part B), 346–356 (2017)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Baader, F., Ganter, B., Sertkaya, B., Sattler, U.: Completing description logic knowledge bases using formal concept analysis. In: Veloso, M.M. (ed.) Proceedings IJCAI 2007, pp. 230–235. AAAI Press (2007)Google Scholar
  9. 9.
    Babin, M.A., Kuznetsov, S.O.: Computing premises of a minimal cover of functional dependencies is intractable. Discrete Appl. Math. 161(6), 742–749 (2013)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Bertet, K., Monjardet, B.: The multiple facets of the canonical direct unit implicational basis. Theor. Comput. Sci. 411(22), 2155–2166 (2010)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Borchmann, D., Hanika, T., Obiedkov, S.: On the usability of probably approximately correct implication bases. In: Bertet, K., Borchmann, D., Cellier, P., Ferré, S. (eds.) ICFCA 2017. LNCS (LNAI), vol. 10308, pp. 72–88. Springer, Cham (2017). Scholar
  12. 12.
    Borchmann, D., Hanika, T., Obiedkov, S.: Probably approximately correct learning of Horn envelopes from queries. Discrete Appl. Math. (2019, in press)Google Scholar
  13. 13.
    Distel, F.: Hardness of enumerating pseudo-intents in the lectic order. In: Kwuida and Sertkaya [25], pp. 124–137CrossRefGoogle Scholar
  14. 14.
    Distel, F., Sertkaya, B.: On the complexity of enumerating pseudo-intents. Discrete Appl. Math. 159(6), 450–466 (2011)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Ganter, B.: Two basic algorithms in concept analysis. In: Kwuida and Sertkaya [25], pp. 312–340CrossRefGoogle Scholar
  16. 16.
    Ganter, B., Obiedkov, S.: Conceptual Exploration. Springer, Heidelberg (2016). Scholar
  17. 17.
    Ganter, B., Wille, R.: Formal Concept Analysis: Mathematical Foundations. Springer, Heidelberg (1999). Scholar
  18. 18.
    Guigues, J.L., Duquenne, V.: Famille minimale d’implications informatives résultant d’un tableau de données binaires. Mathématiques et Sciences Humaines 24(95), 5–18 (1986)Google Scholar
  19. 19.
    Hanika, T., Zumbrägel, J.: Towards collaborative conceptual exploration. In: Chapman, P., Endres, D., Pernelle, N. (eds.) ICCS 2018. LNCS (LNAI), vol. 10872, pp. 120–134. Springer, Cham (2018). Scholar
  20. 20.
    Jäschke, R., Rudolph, S.: Attribute exploration on the web. Preprint (2013).
  21. 21.
    Kautz, H., Kearns, M., Selman, B.: Horn approximations of empirical data. Artif. Intell. 74(1), 129–145 (1995)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Khardon, R.: Translating between Horn representations and their characteristic models. J. Artif. Intell. Res. (JAIR) 3, 349–372 (1995)CrossRefGoogle Scholar
  23. 23.
    Kryszkiewicz, M.: Concise representations of association rules. In: Hand, D.J., Adams, N.M., Bolton, R.J. (eds.) Pattern Detection and Discovery. LNCS (LNAI), vol. 2447, pp. 92–109. Springer, Heidelberg (2002). ISBN 978-3-540-45728-2CrossRefGoogle Scholar
  24. 24.
    Kuznetsov, S.O.: Fitting pattern structures to knowledge discovery in big data. In: Cellier, P., Distel, F., Ganter, B. (eds.) ICFCA 2013. LNCS (LNAI), vol. 7880, pp. 254–266. Springer, Heidelberg (2013). Scholar
  25. 25.
    Kwuida, L., Sertkaya, B. (eds.): ICFCA 2010. LNCS (LNAI), vol. 5986. Springer, Heidelberg (2010). Scholar
  26. 26.
    Obiedkov, S., Romashkin, N.: Collaborative conceptual exploration as a tool for crowdsourcing domain ontologies. In: Proceedings of Russian and South African Workshop on Knowledge Discovery Techniques Based on Formal Concept Analysis, CEUR Workshop Proceedings, vol. 1552, pp. 58–70 (2015)Google Scholar
  27. 27.
    Wild, M.: The joy of implications, aka pure Horn formulas: mainly a survey. Theoretical Computer Science 658, 264–292 (2017)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Faculty of Computer ScienceNational Research University Higher School of EconomicsMoscowRussia

Personalised recommendations