Scalar is Not Enough: Vectorization-based Unbiased Learning to Rank

TL;DR

This paper introduces a vector-based examination hypothesis for unbiased learning to rank, enabling more accurate modeling of complex click behaviors and significantly improving performance over existing methods.

Contribution

It proposes a novel vectorization approach that captures complex interactions in click data, overcoming limitations of scalar-based models.

Findings

Outperforms state-of-the-art ULTR methods on real and simulated click data.

Effectively models complex click behaviors with vector-based approach.

Achieves significant accuracy improvements in ranking tasks.

Abstract

Unbiased learning to rank (ULTR) aims to train an unbiased ranking model from biased user click logs. Most of the current ULTR methods are based on the examination hypothesis (EH), which assumes that the click probability can be factorized into two scalar functions, one related to ranking features and the other related to bias factors. Unfortunately, the interactions among features, bias factors and clicks are complicated in practice, and usually cannot be factorized in this independent way. Fitting click data with EH could lead to model misspecification and bring the approximation error. In this paper, we propose a vector-based EH and formulate the click probability as a dot product of two vector functions. This solution is complete due to its universality in fitting arbitrary click functions. Based on it, we propose a novel model named Vectorization to adaptively learn the relevance embeddings and sort documents by projecting embeddings onto a base vector. Extensive experiments show that our method significantly outperforms the state-of-the-art ULTR methods on complex real clicks as well as simple simulated clicks.