Feature Selection for Analogy-Based Learning to Rank
- 1 Citations
- 678 Downloads
Abstract
Learning to rank based on principles of analogical reasoning has recently been proposed as a novel method in the realm of preference learning. Roughly speaking, the method proceeds from a regularity assumption as follows: Given objects A, B, C, D, if A relates to B as C relates to D, and A is preferred to B, then C is presumably preferred to D. This assumption is formalized in terms of so-called analogical proportions, which operate on a feature representation of the objects. Consequently, a suitable feature representation is an important prerequisite for the success of analogy-based learning to rank. In this paper, we therefore address the problem of feature selection and adapt common feature selection techniques, including forward selection, correlation-based filter techniques, as well as Relief-based methods, to the case of analogical learning. The usefulness of these approaches is shown in experiments with synthetic and benchmark data.
Keywords
Feature selection Leaning to rank Analogical reasoningReferences
- 1.Ahmadi Fahandar, M., Hüllermeier, E.: Learning to rank based on analogical reasoning. In: AAAI (2018)Google Scholar
- 2.Ahmadi Fahandar, M., Hüllermeier, E.: Analogy-based preference learning with kernels. In: Benzmüller, C., Stuckenschmidt, H. (eds.) KI 2019. LNCS (LNAI), vol. 11793, pp. 34–47. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30179-8_3CrossRefGoogle Scholar
- 3.Ahmadi Fahandar, M., Hüllermeier, E., Couso, I.: Statistical inference for incomplete ranking data: the case of rank-dependent coarsening. In: ICML (2017)Google Scholar
- 4.Bounhas, M., Pirlot, M., Prade, H.: Predicting preferences by means of analogical proportions. In: ICCBR (2018)Google Scholar
- 5.Draper, B., Kaito, C., Bins, J.: Iterative relief. In: 2003 Conference on Computer Vision and Pattern Recognition Workshop (2003)Google Scholar
- 6.Fürnkranz, J., Hüllermeier, E.: Preference Learning. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-14125-6CrossRefzbMATHGoogle Scholar
- 7.Geng, Z., Shi, N.Z.: Algorithm AS 257: isotonic regression for umbrella orderings. J. R. Stat. Soc. Seri. C (Appl. Stat.) 39(3), 397–402 (1990)zbMATHGoogle Scholar
- 8.Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. JMLR 3, 1157–1182 (2003)zbMATHGoogle Scholar
- 9.Keogh, E.: Instance-Based Learning, pp. 549–550. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-30164-8_409CrossRefGoogle Scholar
- 10.Kira, K., Rendell, L.A.: The feature selection problem: traditional methods and a new algorithm. In: AAAI (1992)Google Scholar
- 11.Kira, K., Rendell, L.A.: A practical approach to feature selection. In: Proceedings ML-92, 9th International Workshop on Machine Learning (1992)CrossRefGoogle Scholar
- 12.Kononenko, I.: Estimating attributes: analysis and extensions of relief. In: ECML (1994)Google Scholar
- 13.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
- 14.Mirzazadeh, F., Guo, Y., Schuurmans, D.: Convex co-embedding. In: AAAI (2014)Google Scholar
- 15.Sun, Y.: Iterative relief for feature weighting: algorithms, theories, and applications. IEEE TPAMI 29(6), 1035–1051 (2007)CrossRefGoogle Scholar
- 16.Sun, Y., Li, J.: Iterative relief for feature weighting. In: ICML (2006)Google Scholar
- 17.Turner, T., Wollan, P.: Locating a maximum using isotonic regression. Comput. Stat. Data Anal. 25(3), 305–320 (1997)CrossRefGoogle Scholar
- 18.Urbanowicz, R., Meeker, M., LaCava, W., Olson, R., Moore, J.: Relief-based feature selection: introduction and review. J. Biomed. Inform. 85, 189–203 (2017)CrossRefGoogle Scholar
- 19.Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. JMLR 10, 207–244 (2009)zbMATHGoogle Scholar