arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07041cs.LG
收藏

修正链接推荐的暴露偏差

Correcting Exposure Bias for Link Recommendation

Amazon(亚马逊);Carnegie Mellon University(卡内基梅隆大学);Rutgers University(罗格斯大学);Amazon Web Services (AWS) AI Labs(亚马逊云科技(AWS)人工智能实验室)

Shantanu Gupta, Hao Wang, Zachary C. Lipton, Yuyang Wang

摘要:

链接预测方法经常应用于推荐系统中,例如,为学术论文或社交网络中的朋友建议引用。然而,当用户系统性地暴露于某些相关项目时,可能会出现暴露偏差。例如,在引文网络中,作者可能更有可能遇到来自自己领域的论文,从而优先引用它们。这种偏差可以通过简单训练的链接预测器传播,导致有偏差的评估和高泛化误差(如通过真实相关性评估的)。此外,反馈回路可能会加剧这种偏见。我们提出了估计,利用已知的曝光概率,以减轻这种偏见和随之而来的反馈回路。接下来,我们提供了一个损失函数,用于从数据中学习暴露概率。最后,基于真实世界引文网络的半合成数据的实验表明,我们的方法可靠地识别(真正)相关的引文。此外,我们的方法导致推荐论文的研究领域更加多样化。该代码可在https://github.com/shantanu95/exposure-bias-link-rec上获得。

英文摘要:

Link prediction methods are frequently applied in recommender systems, e.g., to suggest citations for academic papers or friends in social networks. However, exposure bias can arise when users are systematically underexposed to certain relevant items. For example, in citation networks, authors might be more likely to encounter papers from their own field and thus cite them preferentially. This bias can propagate through naively trained link predictors, leading to both biased evaluation and high generalization error (as assessed by true relevance). Moreover, this bias can be exacerbated by feedback loops. We propose estimators that leverage known exposure probabilities to mitigate this bias and consequent feedback loops. Next, we provide a loss function for learning the exposure probabilities from data. Finally, experiments on semi-synthetic data based on real-world citation networks, show that our methods reliably identify (truly) relevant citations. Additionally, our methods lead to greater diversity in the recommended papers' fields of study. The code is available at https://github.com/shantanu95/exposure-bias-link-rec.

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。

↑