# Unbiased Learning to Rank with Unbiased Propensity Estimation

arXiv: https://arxiv.org/abs/1804.05938 · HTML: https://mlsanity.com/paper/1804.05938/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2018.

## Built on by (most cited first, 30 of 61)

- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random](https://mlsanity.com/paper/2205.04701/) (2022)
- [Evaluation Methods and Measures for Causal Learning Algorithms](https://mlsanity.com/paper/2202.02896/) (2022)
- [TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations](https://mlsanity.com/paper/2203.10258/) (2022)
- [Respecting Transfer Gap in Knowledge Distillation](https://mlsanity.com/paper/2210.12787/) (2022)
- [Deconfounded Causal Collaborative Filtering](https://mlsanity.com/paper/2110.07122/) (2021)
- [Causal Collaborative Filtering](https://mlsanity.com/paper/2102.01868/) (2021)
- [A Large Scale Search Dataset for Unbiased Learning to Rank](https://mlsanity.com/paper/2207.03051/) (2022)
- [Uncertainty Quantification for Fairness in Two-Stage Recommender Systems](https://mlsanity.com/paper/2205.15436/) (2022)
- [Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset](https://mlsanity.com/paper/2404.02543/) (2024)
- [Towards Disentangling Relevance and Bias in Unbiased Learning to Rank](https://mlsanity.com/paper/2212.13937/) (2022)
- [RankFormer: Listwise Learning-to-Rank Using Listwide Labels](https://mlsanity.com/paper/2306.05808/) (2023)
- [Self-Calibrated Listwise Reranking with Large Language Models](https://mlsanity.com/paper/2411.04602/) (2024)
- [ULTRA: An Unbiased Learning To Rank Algorithm Toolbox](https://mlsanity.com/paper/2108.05073/) (2021)
- [BASM: A Bottom-up Adaptive Spatiotemporal Model for Online Food Ordering Service](https://mlsanity.com/paper/2211.12033/) (2022)
- [Fairness in Matching under Uncertainty](https://mlsanity.com/paper/2302.03810/) (2023)
- [Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce](https://mlsanity.com/paper/2307.16060/) (2023)
- [DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective](https://mlsanity.com/paper/2309.07396/) (2023)
- [Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective](https://mlsanity.com/paper/2306.07528/) (2023)
- [Offline Recommender System Evaluation under Unobserved Confounding](https://mlsanity.com/paper/2309.04222/) (2023)
- [Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions](https://mlsanity.com/paper/2503.00501/) (2025)
- [Bilateral Self-unbiased Learning from Biased Implicit Feedback](https://mlsanity.com/paper/2207.12660/) (2022)
- [The Role of Relevance in Fair Ranking](https://mlsanity.com/paper/2305.05608/) (2023)
- [Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank](https://mlsanity.com/paper/2309.15560/) (2023)
- [Rethinking Position Bias Modeling with Knowledge Distillation for CTR Prediction](https://mlsanity.com/paper/2204.00270/) (2022)
- [Scalar is Not Enough: Vectorization-based Unbiased Learning to Rank](https://mlsanity.com/paper/2206.01702/) (2022)
- [Pessimistic Off-Policy Optimization for Learning to Rank](https://mlsanity.com/paper/2206.02593/) (2022)
- [Whole Page Unbiased Learning to Rank](https://mlsanity.com/paper/2210.10718/) (2022)
- [Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation](https://mlsanity.com/paper/2301.07483/) (2023)
- [Counterfactual Augmentation for Multimodal Learning Under Presentation Bias](https://mlsanity.com/paper/2305.14083/) (2023)

## Abstract (arXiv)

Learning to rank with biased click data is a well-known challenge. A variety of methods has been explored to debias click data for learning to rank such as click models, result interleaving and, more recently, the unbiased learning-to-rank framework based on inverse propensity weighting. Despite their differences, most existing studies separate the estimation of click bias (namely the textitpropensity model) from the learning of ranking algorithms. To estimate click propensities, they either conduct online result randomization, which can negatively affect the user experience, or offline parameter estimation, which has special requirements for click data and is optimized for objectives (e.g. click likelihood) that are not directly related to the ranking performance of the system. In this work, we address those problems by unifying the learning of propensity models and ranking models. We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank. Based on this observation, we propose a Dual Learning Algorithm (DLA) that jointly learns an unbiased ranker and an textitunbiased propensity model. DLA is an automatic unbiased learning-to-rank framework as it directly learns unbiased ranking models from biased click data without any preprocessing. It can adapt to the change of bias distributions and is applicable to online learning. Our empirical experiments with synthetic and real-world data show that the models trained with DLA significantly outperformed the unbiased learning-to-rank algorithms based on result randomization and the models trained with relevance signals extracted by click models.