A Domain Generalization Perspective on Listwise Context Modeling

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.

Accepted to AAAI 2019

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Convolutional Sequence to Sequence Learning
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• A Structured Self-attentive Sentence Embedding
• Generalizing Across Domains via Cross-Gradient Training
• Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems
• Introducing LETOR 4.0 Datasets
• On Application of Learning to Rank for E-Commerce Search
• Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
• ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
• Controllable Invariance through Adversarial Feature Learning
• Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction
• SQL-Rank: A Listwise Approach to Collaborative Ranking