论文标题

通过双层优化公正的隐式反馈

Unbiased Implicit Feedback via Bi-level Optimization

论文作者

Chen, Can, Ma, Chen, Chen, Xi, Song, Sirui, Liu, Hao, Liu, Xue

论文摘要

隐式反馈被广泛利用在推荐系统中,因为它易于收集并提供薄弱的监督信号。最近的作品揭示了隐式反馈和用户项目相关性之间的巨大差距,因为隐式反馈也与项目曝光密切相关。为了弥合这一差距,现有方法明确对暴露量进行了建模,并提出了公正的估计器以提高相关性。不幸的是,这些公正的估计量遭受了较高的梯度差异,尤其是对于长尾项目,导致梯度更新和模型性能退化。为了应对这一挑战,我们从概率的角度提出了一个低变化的无偏估计器,这有效地界定了梯度的差异。与以前的作品不同,该作品要么通过基于启发式的策略估算暴露量或使用大量偏见的训练集,我们建议通过公正的小规模验证集估算暴露量。具体而言,我们首先通过合并用户和项目信息来将用户项目暴露参数化,然后从偏见的培训集中构造无偏见的验证集。通过利用公正的验证集,我们采用双级优化来自动更新与曝光相关的参数以及在学习过程中的推荐模型参数。在两个现实世界数据集和两个半合成数据集上的实验验证了我们方法的有效性。

Implicit feedback is widely leveraged in recommender systems since it is easy to collect and provides weak supervision signals. Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure. To bridge this gap, existing approaches explicitly model the exposure and propose unbiased estimators to improve the relevance. Unfortunately, these unbiased estimators suffer from the high gradient variance, especially for long-tail items, leading to inaccurate gradient updates and degraded model performance. To tackle this challenge, we propose a low-variance unbiased estimator from a probabilistic perspective, which effectively bounds the variance of the gradient. Unlike previous works which either estimate the exposure via heuristic-based strategies or use a large biased training set, we propose to estimate the exposure via an unbiased small-scale validation set. Specifically, we first parameterize the user-item exposure by incorporating both user and item information, and then construct an unbiased validation set from the biased training set. By leveraging the unbiased validation set, we adopt bi-level optimization to automatically update exposure-related parameters along with recommendation model parameters during the learning. Experiments on two real-world datasets and two semi-synthetic datasets verify the effectiveness of our method.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源