arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06859cs.LGcs.AIcs.IR
收藏

LiRank:LinkedIn 工业级大规模排序模型

LiRank: Industrial Large Scale Ranking Models at LinkedIn

LinkedIn(领英)
Fedor Borisyuk, Mingzhou Zhou, Qingquan Song, Siyu Zhu, Birjodh Tiwana, Ganesh Parameswaran, Siddharth Dangi, Lars Hertel, Qiang Xiao, Xiaochen Hou, Yunbo Ouyan… 展开作者

Fedor Borisyuk, Mingzhou Zhou, Qingquan Song, Siyu Zhu, Birjodh Tiwana, Ganesh Parameswaran, Siddharth Dangi, Lars Hertel, Qiang Xiao, Xiaochen Hou, Yunbo Ouyang, Aman Gupta, Sheallika Singh, Dan Liu, Hailing Cheng, Lei Le, Jonathan Hung, Sathiya Keerthi, Ruoyan Wang, Fengyu Zhang, Mohit Kothari, Chen Zhu, Daqi Sun, Yun Dai, Xun Luan, Sirou Zhu, Zhiwei Wang, Neil Daftary, Qianqi Shen, Chengming Jiang, Haichao Wei, Maneesh Varshney, Amol Ghoting, Souvik Ghosh

AI总结:

本文提出 LinkedIn 的大规模排序框架 LiRank,通过 Residual DCN、Dense Gating、Transformers 等架构改进及量化压缩技术,在 Feed、职位推荐和广告 CTR 场景中实现显著指标提升。

摘要:

我们提出 LiRank,这是 LinkedIn 的一个大规模排序框架,将最先进的建模架构和优化方法投入生产。我们揭示了几项建模改进,包括 Residual DCN,它在著名的 DCNv2 架构上增加了注意力机制和残差连接。我们分享了关于组合和调优 SOTA 架构以创建统一模型的见解,包括 Dense Gating、Transformers 和 Residual DCN。我们还提出了新的校准技术,并描述了我们如何将基于深度学习的探索/利用方法产品化。为了实现大规模排序模型的有效、生产级服务,我们详细介绍了如何使用量化和词汇表压缩来训练和压缩模型。我们提供了针对 Feed 排序、职位推荐和广告点击率(CTR)预测等大规模用例的部署设置细节。我们通过阐明最有效的技术方法,总结了从各种 A/B 测试中获得的经验。这些想法为 LinkedIn 的各方面相对指标改进做出了贡献:Feed 的会员会话数增加 +0.5%,职位搜索和推荐的有效职位申请增加 +1.76%,广告 CTR 增加 +4.3%。我们希望这项工作能为有兴趣利用大规模深度排序系统的从业者提供实用的见解和解决方案。

英文摘要:

We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. We unveil several modeling improvements, including Residual DCN, which adds attention and residual connections to the famous DCNv2 architecture. We share insights into combining and tuning SOTA architectures to create a unified model, including Dense Gating, Transformers and Residual DCN. We also propose novel techniques for calibration and describe how we productionalized deep learning based explore/exploit methods. To enable effective, production-grade serving of large ranking models, we detail how to train and compress models using quantization and vocabulary compression. We provide details about the deployment setup for large-scale use cases of Feed ranking, Jobs Recommendations, and Ads click-through rate (CTR) prediction. We summarize our learnings from various A/B tests by elucidating the most effective technical approaches. These ideas have contributed to relative metrics improvements across the board at LinkedIn: +0.5% member sessions in the Feed, +1.76% qualified job applications for Jobs search and recommendations, and +4.3% for Ads CTR. We hope this work can provide practical insights and solutions for practitioners interested in leveraging large-scale deep ranking 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。

↑