Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance
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.
Cite
Text
Köppel et al. "Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019. doi:10.1007/978-3-030-46133-1_15Markdown
[Köppel et al. "Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019.](https://mlanthology.org/ecmlpkdd/2019/koppel2019ecmlpkdd-pairwise/) doi:10.1007/978-3-030-46133-1_15BibTeX
@inproceedings{koppel2019ecmlpkdd-pairwise,
title = {{Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance}},
author = {Köppel, Marius and Segner, Alexander and Wagener, Martin and Pensel, Lukas and Karwath, Andreas and Kramer, Stefan},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2019},
pages = {237-252},
doi = {10.1007/978-3-030-46133-1_15},
url = {https://mlanthology.org/ecmlpkdd/2019/koppel2019ecmlpkdd-pairwise/}
}