# Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank

arXiv: https://arxiv.org/abs/2102.05990 · HTML: https://mlsanity.com/paper/2102.05990/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 53 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Introducing LETOR 4.0 Datasets](https://mlsanity.com/paper/1306.2597/) (2013)
- [Cascading Bandits: Learning to Rank in the Cascade Model](https://mlsanity.com/paper/1502.02763/) (2015)
- [Conservative Bandits](https://mlsanity.com/paper/1602.04282/) (2016)
- [Estimating Position Bias without Intrusive Interventions](https://mlsanity.com/paper/1812.05161/) (2018)
- [Multiple-Play Bandits in the Position-Based Model](https://mlsanity.com/paper/1606.02448/) (2016)
- [Differentiable Unbiased Online Learning to Rank](https://mlsanity.com/paper/1809.08415/) (2018)
- [DCM Bandits: Learning to Rank with Multiple Clicks](https://mlsanity.com/paper/1602.03146/) (2016)
- [Unifying Online and Counterfactual Learning to Rank](https://mlsanity.com/paper/2012.04426/) (2020)
- [Safe Exploration for Optimizing Contextual Bandits](https://mlsanity.com/paper/2002.00467/) (2020)
- [To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions](https://mlsanity.com/paper/1907.06412/) (2019)
- [Optimizing Ranking Models in an Online Setting](https://mlsanity.com/paper/1901.10262/) (2019)

## Built on by (most cited first, 6 of 6)

- [Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank](https://mlsanity.com/paper/2203.17118/) (2022)
- [Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization](https://mlsanity.com/paper/2305.01522/) (2023)
- [Practical and Robust Safety Guarantees for Advanced Counterfactual Learning to Rank](https://mlsanity.com/paper/2407.19943/) (2024)
- [Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking](https://mlsanity.com/paper/2204.13765/) (2022)
- [Composing Efficient, Robust Tests for Policy Selection](https://mlsanity.com/paper/2306.07372/) (2023)
- [Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank](https://mlsanity.com/paper/2409.09881/) (2024)

## Abstract (arXiv)

Existing work in counterfactual Learning to Rank (LTR) has focussed on optimizing feature-based models that predict the optimal ranking based on document features. LTR methods based on bandit algorithms often optimize tabular models that memorize the optimal ranking per query. These types of model have their own advantages and disadvantages. Feature-based models provide very robust performance across many queries, including those previously unseen, however, the available features often limit the rankings the model can predict. In contrast, tabular models can converge on any possible ranking through memorization. However, memorization is extremely prone to noise, which makes tabular models reliable only when large numbers of user interactions are available. Can we develop a robust counterfactual LTR method that pursues memorization-based optimization whenever it is safe to do? We introduce the Generalization and Specialization (GENSPEC) algorithm, a robust feature-based counterfactual LTR method that pursues per-query memorization when it is safe to do so. GENSPEC optimizes a single feature-based model for generalization: robust performance across all queries, and many tabular models for specialization: each optimized for high performance on a single query. GENSPEC uses novel relative high-confidence bounds to choose which model to deploy per query. By doing so, GENSPEC enjoys the high performance of successfully specialized tabular models with the robustness of a generalized feature-based model. Our results show that GENSPEC leads to optimal performance on queries with sufficient click data, while having robust behavior on queries with little or noisy data.