arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.08480cs.IRcs.LG
收藏

非点击意味着无关?倾向比评分作为校正

Non-Clicks Mean Irrelevant? Propensity Ratio Scoring As a Correction

University of Virginia(弗吉尼亚大学);Google Research(谷歌研究院)

Nan Wang, Zhen Qin, Xuanhui Wang, Hongning Wang

摘要:

无偏学习排序(LTR)的最新进展依靠逆倾向评分(IPS)来消除隐式反馈中的偏差。虽然理论上可以纠正将点击的文档视为相关文档所引入的偏见,但IPS忽略了(隐含地)将未点击的文档视为不相关文档所引起的偏见。在这项工作中,我们首先严格证明,这种使用的点击数据导致不必要的成对比较相关的文件,防止无偏排名优化。基于证明,我们推导出一个简单而合理的新的加权方案,称为倾向比评分(PRS),它提供了治疗点击和非点击。除了纠正点击中的偏差外,PRS还避免了LTR训练中的相关文档比较,并且具有较低的可变性。我们广泛的实证评估证实,PRS确保更有效地使用点击数据和改进的性能,无论是合成数据从一组LTR基准,以及在现实世界中的大规模数据从Gmail搜索。

英文摘要:

Recent advances in unbiased learning to rank (LTR) count on Inverse Propensity Scoring (IPS) to eliminate bias in implicit feedback. Though theoretically sound in correcting the bias introduced by treating clicked documents as relevant, IPS ignores the bias caused by (implicitly) treating non-clicked ones as irrelevant. In this work, we first rigorously prove that such use of click data leads to unnecessary pairwise comparisons between relevant documents, which prevent unbiased ranker optimization. Based on the proof, we derive a simple yet well justified new weighting scheme, called Propensity Ratio Scoring (PRS), which provides treatments on both clicks and non-clicks. Besides correcting the bias in clicks, PRS avoids relevant-relevant document comparisons in LTR training and enjoys a lower variability. Our extensive empirical evaluations confirm that PRS ensures a more effective use of click data and improved performance in both synthetic data from a set of LTR benchmarks, as well as in the real-world large-scale data from GMail search.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑