Plackett-Luce model for learning-to-rank task

TL;DR

This paper introduces ListMLE, a non-linear list-wise learning-to-rank algorithm using the Plackett-Luce loss, which outperforms or matches state-of-the-art systems on large real-world datasets.

Contribution

The paper presents a novel list-wise learning-to-rank method, ListMLE, that achieves superior performance on real-world datasets, surpassing existing models.

Findings

ListMLE matches or exceeds state-of-the-art systems.

First single-model list-wise system to outperform in real-world data.

Demonstrates effectiveness on Yahoo and Microsoft datasets.

Abstract

List-wise based learning to rank methods are generally supposed to have better performance than point- and pair-wise based. However, in real-world applications, state-of-the-art systems are not from list-wise based camp. In this paper, we propose a new non-linear algorithm in the list-wise based framework called ListMLE, which uses the Plackett-Luce (PL) loss. Our experiments are conducted on the two largest publicly available real-world datasets, Yahoo challenge 2010 and Microsoft 30K. This is the first time in the single model level for a list-wise based system to match or overpass state-of-the-art systems in real-world datasets.