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 2202.06499cs.LGcs.IR
收藏

真实世界大规模推荐系统的可复制性和平滑激活

Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations

Google(谷歌公司)

Gil I. Shamir, Dong Lin

摘要:

现实世界的推荐系统影响着不断增长的领域。有了深度网络,现在驱动这样的系统,推荐与用户的兴趣和任务更加相关。然而,即使由相同系统为相同用户、推荐序列、请求或查询产生,它们也可能不总是可再现的。这个问题在学术出版物中几乎没有受到关注,但事实上,在实际生产系统中非常现实和关键。我们考虑真实的大规模深层模型的再现性,其预测决定了这样的建议。我们证明了在深度模型中使用的著名的校正线性单元(ReLU)激活可能是不可再现性的主要贡献者。我们建议使用平滑激活来提高推荐的可重复性。我们描述了一个新的平滑激活家族; Smooth ReLU(SmeLU),旨在通过数学简单性提高再现性,并具有潜在的更便宜的实现。SmeLU是一个更广泛的平滑激活家族的成员。虽然其他提高真实系统再现性的技术通常以精度为代价,但平滑激活不仅可以提高再现性,甚至可以提高精度。我们报告了来自真实系统的指标,在这些系统中,我们能够生产SmeLU,具有显著的再现性增益和更好的准确性-再现性权衡。这些包括点击率(CTR)预测系统,内容和应用程序推荐系统。

英文摘要:

Real world recommendation systems influence a constantly growing set of domains. With deep networks, that now drive such systems, recommendations have been more relevant to the user's interests and tasks. However, they may not always be reproducible even if produced by the same system for the same user, recommendation sequence, request, or query. This problem received almost no attention in academic publications, but is, in fact, very realistic and critical in real production systems. We consider reproducibility of real large scale deep models, whose predictions determine such recommendations. We demonstrate that the celebrated Rectified Linear Unit (ReLU) activation, used in deep models, can be a major contributor to irreproducibility. We propose the use of smooth activations to improve recommendation reproducibility. We describe a novel family of smooth activations; Smooth ReLU (SmeLU), designed to improve reproducibility with mathematical simplicity, with potentially cheaper implementation. SmeLU is a member of a wider family of smooth activations. While other techniques that improve reproducibility in real systems usually come at accuracy costs, smooth activations not only improve reproducibility, but can even give accuracy gains. We report metrics from real systems in which we were able to productionalize SmeLU with substantial reproducibility gains and better accuracy-reproducibility trade-offs. These include click-through-rate (CTR) prediction systems, content, and application recommendation systems.

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。

↑