Advertisement

Analogy-Based Preference Learning with Kernels

  • Mohsen Ahmadi FahandarEmail author
  • Eyke Hüllermeier
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11793)

Abstract

Building on a specific formalization of analogical relationships of the form “A relates to B as C relates to D”, we establish a connection between two important subfields of artificial intelligence, namely analogical reasoning and kernel-based learning. More specifically, we show that so-called analogical proportions are closely connected to kernel functions on pairs of objects. Based on this result, we introduce the analogy kernel, which can be seen as a measure of how strongly four objects are in analogical relationship. As an application, we consider the problem of object ranking in the realm of preference learning, for which we develop a new method based on support vector machines trained with the analogy kernel. Our first experimental results for data sets from different domains (sports, education, tourism, etc.) are promising and suggest that our approach is competitive to state-of-the-art algorithms in terms of predictive accuracy.

References

  1. 1.
    Ahmadi Fahandar, M., Hüllermeier, E.: Learning to rank based on analogical reasoning. In: Proceedings AAAI-2018, 32th AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp. 2951–2958 (2018)Google Scholar
  2. 2.
    Ahmadi Fahandar, M., Hüllermeier, E., Couso, I.: Statistical inference for incomplete ranking data: the case of rank-dependent coarsening. In: Proceedings ICML-2017, 34th International Conference on Machine Learning, vol. 70, pp. 1078–1087. PMLR, International Convention Centre, Sydney, Australia (2017)Google Scholar
  3. 3.
    Beltran, W.C., Jaudoin, H., Pivert, O.: Analogical prediction of null values: the numerical attribute case. In: Manolopoulos, Y., Trajcevski, G., Kon-Popovska, M. (eds.) ADBIS 2014. LNCS, vol. 8716, pp. 323–336. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10933-6_24CrossRefGoogle Scholar
  4. 4.
    Beltran, W.C., Prade, H., Richard, G.: Constructive solving of Raven’s IQ tests with analogical proportions. Int. J. Intell. Syst. 31(11), 1072–1103 (2016)CrossRefGoogle Scholar
  5. 5.
    Billingsley, R., Prade, H., Richard, G., Williams, M.-A.: Towards analogy-based decision - a proposal. In: Christiansen, H., Jaudoin, H., Chountas, P., Andreasen, T., Legind Larsen, H. (eds.) FQAS 2017. LNCS (LNAI), vol. 10333, pp. 28–35. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59692-1_3CrossRefGoogle Scholar
  6. 6.
    Bounhas, M., Pirlot, M., Prade, H.: Predicting preferences by means of analogical proportions. In: Cox, M.T., Funk, P., Begum, S. (eds.) ICCBR 2018. LNCS (LNAI), vol. 11156, pp. 515–531. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01081-2_34CrossRefGoogle Scholar
  7. 7.
    Bounhas, M., Prade, H., Richard, G.: Analogical classification: a new way to deal with examples. In: Proceedings ECAI-2014, 21th European Conference on Artificial Intelligence, Czech Republic, Prague, pp. 135–140 (2014)Google Scholar
  8. 8.
    Bounhas, M., Prade, H., Richard, G.: Analogy-based classifiers for nominal or numerical data. Int. J. Approx. Reason. 91, 36–55 (2017)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Bradley, R., Terry, M.: The rank analysis of incomplete block designs I. The method of paired comparisons. Biometrika 39, 324–345 (1952)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Burges, C., et al.: Learning to rank using gradient descent. In: Proceedings ICML-2005, 22th International Conference on Machine Learning, Bonn, Germany, pp. 89–96. ACM (2005)Google Scholar
  11. 11.
    Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: from pairwise approach to listwise approach. In: Proceedings ICML-2007, 24th International Conference on Machine Learning, pp. 129–136 (2007)Google Scholar
  12. 12.
    Cheng, W., Hühn, J., Hüllermeier, E.: Decision tree and instance-based learning for label ranking. In: Proceedings ICML-2009, 26th International Conference on Machine Learning, pp. 161–168. ACM, New York (2009)Google Scholar
  13. 13.
    Cohen, W.W., Schapire, R.E., Singer, Y.: Learning to order things. J. Artif. Intell. Res. 10(1), 243–270 (1999)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Dubois, D., Prade, H., Richard, G.: Multiple-valued extensions of analogical proportions. Fuzzy Sets Syst. 292, 193–202 (2016)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Fürnkranz, J., Hüllermeier, E.: Preference Learning. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-14125-6CrossRefzbMATHGoogle Scholar
  16. 16.
    Fürnkranz, J., Hüllermeier, E., Vanderlooy, S.: Binary decomposition methods for multipartite ranking. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS (LNAI), vol. 5781, pp. 359–374. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-04180-8_41CrossRefGoogle Scholar
  17. 17.
    Har-Peled, S., Roth, D., Zimak, D.: Constraint classification: a new approach to multiclass classification. In: Cesa-Bianchi, N., Numao, M., Reischuk, R. (eds.) ALT 2002. LNCS (LNAI), vol. 2533, pp. 365–379. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-36169-3_29CrossRefGoogle Scholar
  18. 18.
    Hastie, T., Rosset, S., Tibshirani, R., Zhu, J.: The entire regularization path for the support vector machine. J. Mach. Learn. Res. 5, 1391–1415 (2004)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Hug, N., Prade, H., Richard, G., Serrurier, M.: Analogy in recommendation. Numerical vs. ordinal: a discussion. In: FUZZ-IEEE-2016, IEEE International Conference on Fuzzy Systems, Vancouver, BC, Canada, pp. 2220–2226 (2016)Google Scholar
  20. 20.
    Joachims, T.: Optimizing search engines using clickthrough data. In: Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2002), pp. 133–142. ACM Press (2002)Google Scholar
  21. 21.
    Kamishima, T., Kazawa, H., Akaho, S.: A survey and empirical comparison of object ranking methods. In: Fürnkranz, J., Hüllermeier, E. (eds.) Preference Learning, pp. 181–202. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-14125-6_9CrossRefGoogle Scholar
  22. 22.
    Kamishima, T., Akaho, S.: Supervised ordering by regression combined with thurstone’s model. Artif. Intell. Rev. 25(3), 231–246 (2006)CrossRefGoogle Scholar
  23. 23.
    Kolmogorov, A.: Sulla determinazione empirica di una legge di distribuzione. Giornale dell’Istituto Italiano degli Attuari 4, 83–91 (1933)zbMATHGoogle Scholar
  24. 24.
    Mercer, J.: Functions of positive and negative type, and their connection with the theory of integral equations. Philos. Trans. R. Soc. Lond. Ser. A 209, 415–446 (1909)CrossRefGoogle Scholar
  25. 25.
    Miclet, L., Prade, H.: Handling analogical proportions in classical logic and fuzzy logics settings. In: Sossai, C., Chemello, G. (eds.) ECSQARU 2009. LNCS (LNAI), vol. 5590, pp. 638–650. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-02906-6_55CrossRefzbMATHGoogle Scholar
  26. 26.
    Moser, B.: On representing and generating kernels by fuzzy equivalence relations. J. Mach. Learn. Res. 7, 2603–2620 (2006)MathSciNetzbMATHGoogle Scholar
  27. 27.
    Pirlot, M., Prade, H., Richard, G.: Completing preferences by means of analogical proportions. In: Torra, V., Narukawa, Y., Navarro-Arribas, G., Yañez, C. (eds.) MDAI 2016. LNCS (LNAI), vol. 9880, pp. 135–147. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-45656-0_12CrossRefGoogle Scholar
  28. 28.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, pp. 61–74. MIT Press (1999)Google Scholar
  29. 29.
    Prade, H., Richard, G.: Analogical proportions and analogical reasoning - an introduction. In: Aha, D.W., Lieber, J. (eds.) ICCBR 2017. LNCS (LNAI), vol. 10339, pp. 16–32. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-61030-6_2CrossRefGoogle Scholar
  30. 30.
    Schölkopf, B.: The kernel trick for distances. In: Proceedings NIPS-2000, 13th International Conference on Neural Information Processing Systems, pp. 301–307. MIT Press (2001)Google Scholar
  31. 31.
    Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998)CrossRefGoogle Scholar
  32. 32.
    Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2001)Google Scholar
  33. 33.
    Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, New York (2004)CrossRefGoogle Scholar
  34. 34.
    Vembu, S., Gärtner, T.: Label ranking algorithms: a survey. In: Fürnkranz, J., Hüllermeier, E. (eds.) Preference Learning, pp. 45–64. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-14125-6_3CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Heinz Nixdorf Institute and Department of Computer Science, Intelligent Systems and Machine Learning GroupPaderborn UniversityPaderbornGermany

Personalised recommendations