arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.13892cs.IRcs.LGstat.ME
收藏

去偏推荐系统中的跨数据集倾向估计

Cross-Dataset Propensity Estimation for Debiasing Recommender Systems

Cornell University(康奈尔大学)

Fengyu Li, Sarah Dean

摘要:

用于推荐系统训练的数据集往往会受到用户和商家选择偏差引起的分布偏移的影响。本文研究了选择偏差对不同量化数据集的影响。然后,我们利用来自不同源分布的两个不同量化的数据集,通过应用来自因果推理的逆概率评分方法来减轻分布偏移。从经验上讲,我们的方法比单数据集方法和组合两个数据集的替代方法获得了显着的性能改进。

英文摘要:

Datasets for training recommender systems are often subject to distribution shift induced by users' and recommenders' selection biases. In this paper, we study the impact of selection bias on datasets with different quantization. We then leverage two differently quantized datasets from different source distributions to mitigate distribution shift by applying the inverse probability scoring method from causal inference. Empirically, our approach gains significant performance improvement over single-dataset methods and alternative ways of combining two datasets.

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。

↑