Litcius/Paper detail

Revisiting Two-tower Models for Unbiased Learning to Rank

Le Yan, Zhen Qin, Honglei Zhuang, Xuanhui Wang, Michael Bendersky, Marc Najork

2022Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval18 citationsDOIOpen Access PDF

Abstract

Two-tower architecture is commonly used in real-world systems for Unbiased Learning to Rank (ULTR), where a Deep Neural Network (DNN) tower models unbiased relevance predictions, while another tower models observation biases inherent in the training data like user clicks. This two-tower architecture introduces inductive biases to allow more efficient use of limited observational logs and better generalization during deployment than single-tower architecture that may learn spurious correlations between relevance predictions and biases. However, despite their popularity, it is largely neglected in the literature that existing two-tower models assume that the joint distribution of relevance prediction and observation probabilities are completely factorizable. In this work, we revisit two-tower models for ULTR. We rigorously show that the factorization assumption can be too strong for real-world user behaviors, and existing methods may easily fail under slightly milder assumptions. We then propose several novel ideas that consider a wider spectrum of user behaviors while still under the two-tower framework to maintain simplicity and generalizability. Our concerns of existing two-tower models and the effectiveness of our proposed methods are validated on both controlled synthetic and large-scale real-world datasets.

Topics & Concepts

Computer scienceGeneralizability theoryTowerGeneralizationSpurious relationshipMachine learningRelevance (law)Bootstrapping (finance)Artificial intelligenceExtrapolationMathematicsStatisticsEconometricsEngineeringLawCivil engineeringPolitical scienceMathematical analysisData Stream Mining TechniquesRecommender Systems and TechniquesDomain Adaptation and Few-Shot Learning
Revisiting Two-tower Models for Unbiased Learning to Rank | Litcius