A Domain Generalization Perspective on Listwise Context Modeling

TL;DR

This paper introduces QILCM, a neural model for learning query-invariant representations in listwise ranking, improving generalization to unseen queries in information retrieval tasks.

Contribution

It proposes a novel domain generalization approach with a neural architecture that learns query-invariant features for better ranking generalization.

Findings

QILCM outperforms state-of-the-art methods on benchmark datasets.

Learning query-invariant representations enhances generalization to unseen queries.

The approach effectively reduces inter-query variability impact.

Abstract

As one of the most popular techniques for solving the ranking problem in information retrieval, Learning-to-rank (LETOR) has received a lot of attention both in academia and industry due to its importance in a wide variety of data mining applications. However, most of existing LETOR approaches choose to learn a single global ranking function to handle all queries, and ignore the substantial differences that exist between queries. In this paper, we propose a domain generalization strategy to tackle this problem. We propose Query-Invariant Listwise Context Modeling (QILCM), a novel neural architecture which eliminates the detrimental influence of inter-query variability by learning \textit{query-invariant} latent representations, such that the ranking system could generalize better to unseen queries. We evaluate our techniques on benchmark datasets, demonstrating that QILCM outperforms previous state-of-the-art approaches by a substantial margin.