paper-with-me

홈 › Papers

Cascade Model-based Propensity Estimation for Counterfactual Learning to Rank

2020-05-25 · Ali Vardasbi, Maarten de Rijke, Ilya Markov

Unbiased CLTR requires click propensities to compensate for the difference between user clicks and true relevance of search results via IPS. Current propensity estimation methods assume that user click behavior follows the PBM and estimate click propensities based on this assumption. However, in reality, user clicks often follow the CM, where users scan search results from top to bottom and where each next click depends on the previous one. In this cascade scenario, PBM-based estimates of propensities are not accurate, which, in turn, hurts CLTR performance. In this paper, we propose a propensity estimation method for the cascade scenario, called CM-IPS. We show that CM-IPS keeps CLTR performance close to the full-information performance in case the user clicks follow the CM, while PBM-based CLTR has a significant gap towards the full-information. The opposite is true if the user clicks follow PBM instead of the CM. Finally, we suggest a way to select between CM- and PBM-based propensity estimation methods based on historical user clicks.

📄 PDF Abstract BibTeX arXiv:2005.11938

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualLearning-To-Rank

Similar Papers 제목 키워드 기반

Counterfactual Learning to Rank using Heterogeneous Treatment Effect Estimation

2020-07-19 · Mucun Tian, Chun Guo, Vito Ostuni, Zhen Zhu

Learning-to-Rank (LTR) models trained from implicit feedback (e.g. clicks) suffer from inherent biases. A well-known one is the position bias -- documents in top positions are more likely to receive clicks due in part to…

counterfactualHeterogeneous Treatment Effect EstimationLearning-To-RankPosition

Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study

2024-04-04 · Zechun Niu, Jiaxin Mao, Qingyao Ai, Ji-Rong Wen

Counterfactual learning to rank (CLTR) has attracted extensive attention in the IR community for its ability to leverage massive logged user interaction data to train ranking models. While the CLTR models can be theoreti…

counterfactualLearning-To-RankUser Simulation

Consistent Position Bias Estimation without Online Interventions for Learning-to-Rank

2018-06-09 · Aman Agarwal, Ivan Zaitsev, Thorsten Joachims

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal with uninformative signals due to position in the ranking, saliency, and other p…

counterfactualLearning-To-RankPosition

Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank

2022-03-31 · Harrie Oosterhuis

Clicks on rankings suffer from position-bias: generally items on lower ranks are less likely to be examined - and thus clicked - by users, in spite of their actual preferences between items. The prevalent approach to unb…

counterfactualGeneral Reinforcement LearningLearning-To-RankPosition

Estimating Position Bias without Intrusive Interventions

2018-12-12 · Agarwal Aman, Zaitsev Ivan, Wang Xuanhui, Li Cheng 외

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal. While it was recently shown how counterfactual learning-to-rank (LTR) approache…

counterfactualLearning-To-RankPosition