Abstract
We present a pairwise learning to rank approach based on a neural net, called DirectRanker, that generalizes the RankNet architecture. We show mathematically that our model is reflexive, antisymmetric, and transitive allowing for simplified training and improved performance. Experimental results on the LETOR MSLR-WEB10K, MQ2007 and MQ2008 datasets show that our model outperforms numerous state-of-the-art methods, while being inherently simpler in structure and using a pairwise approach only.
M. Köppel, A. Segner and M. Wagener—These authors contributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For our implementation of the model and the tests see https://github.com/kramerlab/direct-ranker.
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/
Burges, C., et al.: Learning to rank using gradient descent. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 89–96. ACM, New York (2005). http://doi.acm.org/10.1145/1102351.1102363
Burges, C., Ragno, R., Le, Q., Burges, C.J.: Learning to rank with non-smooth cost functions. In: Advances in Neural Information Processing Systems 19. MIT Press, Cambridge, January 2007. https://www.microsoft.com/en-us/research/publication/learning-to-rank-with-non-smooth-cost-functions/
Cao, Y., Xu, J., Liu, T.Y., Li, H., Huang, Y., Hon, H.W.: Adapting ranking SVM to document retrieval. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 186–193. ACM (2006). https://doi.org/10.1145/1148170.1148205
Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: from pairwise approach to listwise approach, p. 9, April 2007. https://www.microsoft.com/en-us/research/publication/learning-to-rank-from-pairwise-approach-to-listwise-approach/
Cooper, W.S., Gey, F.C., Dabney, D.P.: Probabilistic retrieval based on staged logistic regression. In: Proceedings of the 15th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 198–210. ACM (1992). http://doi.acm.org/10.1145/133160.133199
Freund, Y., Iyer, R., Schapire, R.E., Singer, Y.: An efficient boosting algorithm for combining preferences. J. Mach. Learn. Res. 4(Nov), 933–969 (2003). http://dl.acm.org/citation.cfm?id=945365.964285
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2000). http://www.jstor.org/stable/2699986
Fuhr, N.: Optimum polynomial retrieval functions based on the probability ranking principle. ACM Trans. Inf. Syst. (TOIS) 7(3), 183–204 (1989)
Herbrich, R., Graepel, T., Obermayer, K.: Large margin rank boundaries for ordinal regression. In: Advances in Large Margin Classifiers, pp. 115–132 (2000)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989). https://doi.org/10.1016/0893-6080(89)90020-8
Ibrahim, O.A.S., Landa-Silva, D.: ES-Rank: evolution strategy learning to rank approach. In: Proceedings of the Symposium on Applied Computing, pp. 944–950. ACM (2017). https://doi.org/10.1145/3019612.3019696
Ibrahim, O.A.S., Landa-Silva, D.: An evolutionary strategy with machine learning for learning to rank in information retrieval. Soft Comput. 22(10), 3171–3185 (2018). https://doi.org/10.1007/s00500-017-2988-6
Jiang, L., Li, C., Cai, Z.: Learning decision tree for ranking. Knowl. Inf. Syst. 20(1), 123–135 (2009)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Li, P., Wu, Q., Burges, C.J.: McRank: learning to rank using multiple classification and gradient boosting. In: Advances in Neural Information Processing Systems, pp. 897–904 (2008)
Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3(3), 225–331 (2009). https://doi.org/10.1561/1500000016
Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Qin, T., Liu, T.: Introducing LETOR 4.0 datasets. CoRR abs/1306.2597 (2013). http://arxiv.org/abs/1306.2597
Rigutini, L., Papini, T., Maggini, M., Bianchini, M.: A neural network approach for learning object ranking. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008. LNCS, vol. 5164, pp. 899–908. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87559-8_93
Croft, W.B., Callan, J.: Lemur toolkit (2001–2012). http://lemurproject.org/contrib.php
Wu, Q., Burges, C.J., Svore, K.M., Gao, J.: Adapting boosting for information retrieval measures. Inf. Retr. 13, 254–270 (2010). https://www.microsoft.com/en-us/research/publication/adapting-boosting-for-information-retrieval-measures/
Xu, J., Li, H.: AdaRank: a boosting algorithm for information retrieval. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2007, pp. 391–398. ACM, New York (2007). https://doi.org/10.1145/1277741.1277809
Acknowledgement
We would like to thank Dr. Christian Schmitt for his contributions to the work presented in this paper.
We also thank Luiz Frederic Wagner for proof(read)ing the mathematical aspects of our model.
Parts of this research were conducted using the supercomputer Mogon and/or advisory services offered by Johannes Gutenberg University Mainz (hpc.uni-mainz.de), which is a member of the AHRP (Alliance for High Performance Computing in Rhineland Palatinate, www.ahrp.info) and the Gauss Alliance e.V.
The authors gratefully acknowledge the computing time granted on the supercomputer Mogon at Johannes Gutenberg University Mainz (hpc.uni-mainz.de).
This research was partially funded by the Carl Zeiss Foundation Project: ‘Competence Centre for High-Performance-Computing in the Natural Sciences’ at the University of Mainz. Furthermore, Andreas Karwath has been co-funded by the MRC grant MR/S003991/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Köppel, M., Segner, A., Wagener, M., Pensel, L., Karwath, A., Kramer, S. (2020). Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019. Lecture Notes in Computer Science(), vol 11908. Springer, Cham. https://doi.org/10.1007/978-3-030-46133-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-46133-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46132-4
Online ISBN: 978-3-030-46133-1
eBook Packages: Computer ScienceComputer Science (R0)