arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.01985cs.IR
收藏

在工业约束下改进 Pinterest 的特征交互

Improving feature interactions at Pinterest under industry constraints

Siddarth Malreddy, Matthew Lawhon, Usha Amrutha Nookala, Aditya Mantha, Dhruvil Deven Badani

AI总结:

本文总结 Pinterest 在延迟、GPU 显存和可复现性等工业约束下改进 Homefeed 排序模型特征交互的挑战、策略、权衡与架构选择实验。

摘要:

由于独特的约束条件,在工业环境中采用推荐系统的先进技术往往具有挑战性。本文旨在通过特征交互这一视角突出这些约束。特征交互对于在推荐系统和在线广告中准确预测用户行为至关重要。尽管许多新技术在 Criteo 等基准数据集上表现出优越性能,但它们在工业环境中的直接应用受到模型延迟、GPU 内存限制和模型可复现性等约束的阻碍。在本文中,我们分享了在上述约束下改进 Pinterest Homefeed 排序模型中特征交互的经验。我们详细介绍了遇到的具体挑战、为应对这些挑战所采用的策略,以及为平衡性能与实际限制而作出的权衡。此外,我们还提出了一组学习实验,以帮助指导特征交互架构的选择。我们相信,这些见解将对那些有兴趣通过更好的特征交互学习来改进模型的工程师有所帮助。

英文摘要:

Adopting advances in recommendation systems is often challenging in industrial settings due to unique constraints. This paper aims to highlight these constraints through the lens of feature interactions. Feature interactions are critical for accurately predicting user behavior in recommendation systems and online advertising. Despite numerous novel techniques showing superior performance on benchmark datasets like Criteo, their direct application in industrial settings is hindered by constraints such as model latency, GPU memory limitations and model reproducibility. In this paper, we share our learnings from improving feature interactions in Pinterest's Homefeed ranking model under such constraints. We provide details about the specific challenges encountered, the strategies employed to address them, and the trade-offs made to balance performance with practical limitations. Additionally, we present a set of learning experiments that help guide the feature interaction architecture selection. We believe these insights will be useful for engineers who are interested in improving their model through better feature interaction learning.

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。

↑