A General Framework for Pairwise Unbiased Learning to Rank
arXiv:2207.08537 · doi:10.1145/3539813.3545119
Abstract
Pairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing approaches. In this paper, we develop an approach based on a minimalistic set of assumptions that can be applied to a much broader range of user browsing patterns and arbitrary presentation layouts. We implement the approach as a simplified version of the Unbiased LambdaMART and demonstrate that it retains the underlying unbiasedness property in a wider variety of settings than the original algorithm. Finally, using simulations with "golden" relevance labels, we will show that the simplified version compares favourably with the original Unbiased LambdaMART when the examination of different positions in a ranked list is not assumed to be independent.
arXiv comment10 pages
References in corpus (7)
- Bias and Debias in Recommender System: A Survey and Future Directions
- Counterfactual Risk Minimization: Learning from Logged Bandit Feedback
- Estimating Position Bias without Intrusive Interventions
- Differentiable Unbiased Online Learning to Rank
- Unifying Online and Counterfactual Learning to Rank
- Intervention Harvesting for Context-Dependent Examination-Bias Estimation
- Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model