提出新模型捕捉用户点击倾向，解决排序中因信息满足导致的点击偏差。
Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance
- 基于查询层级点击倾向建模，捕捉用户只点少数结果的行为。
- 在百度真实数据集上显著优于现有最先进方法，提升排序准确性。
- 适合关注真实搜索场景下排序公平性与用户行为建模的研究者。
现有无偏学习排序（ULTR）方法多基于用户检视假设，即用户仅当结果既相关又可见（通常由位置决定）时才会点击。但在实际场景中，用户常在浏览多个相关结果后仅点击一两个，因耐心有限或需求已满足。为此，我们提出查询层级点击倾向模型，捕捉用户对不同结果列表的点击概率，允许观察到的相关结果仍存在未点击的非零概率。我们假设该倾向随潜在相关结果增多而上升，称此现象为相关性饱和偏差。提出双层级逆倾向加权（DualIPW）机制，结合查询级与位置级加权，同时缓解相关性饱和与位置偏差。理论推导证明DualIPW可学习无偏排序模型。在真实世界百度-ULTR数据集上的实验表明，该方法显著优于当前最先进基线。
原文摘要 · Abstract (English)
Most existing unbiased learning-to-rank (ULTR) approaches are based on the user examination hypothesis, which assumes that users will click a result only if it is both relevant and observed (typically modeled by position). However, in real-world scenarios, users often click only one or two results after examining multiple relevant options, due to limited patience or because their information needs have already been satisfied. Motivated by this, we propose a query-level click propensity model to capture the probability that users will click on different result lists, allowing for non-zero probabilities that users may not click on an observed relevant result. We hypothesize that this propensity increases when more potentially relevant results are present, and refer to this user behavior as relevance saturation bias. Our method introduces a Dual Inverse Propensity Weighting (DualIPW) mechanism -- combining query-level and position-level IPW -- to address both relevance saturation and position bias. Through theoretical derivation, we prove that DualIPW can learn an unbiased ranking model. Experiments on the real-world Baidu-ULTR dataset demonstrate that our approach significantly outperforms state-of-the-art ULTR baselines. The code and dataset information can be found at https://github.com/Trustworthy-Information-Access/DualIPW.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。