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 2410.20868cs.IR
收藏

RecFlow:一个工业级全流程推荐数据集

RecFlow: An Industrial Full Flow Recommendation Dataset

Qi Liu, Kai Zheng, Rui Huang, Wuchao Li, Kuo Cai, Yuan Chai, Yanan Niu, Yiqun Hui, Bing Han, Na Mou, Hongning Wang, Wentian Bao, Yunen Yu, Guorui Zhou, Han Li, … 展开作者

Qi Liu, Kai Zheng, Rui Huang, Wuchao Li, Kuo Cai, Yuan Chai, Yanan Niu, Yiqun Hui, Bing Han, Na Mou, Hongning Wang, Wentian Bao, Yunen Yu, Guorui Zhou, Han Li, Yang Song, Defu Lian, Kun Gai

AI总结:

本文发布工业级全流程推荐数据集RecFlow,覆盖曝光与各阶段未曝光物品及6个阶段样本,以支持多阶段推荐、去偏和用户行为建模研究。

摘要:

工业推荐系统(RS)依赖多阶段流水线,在从海量语料库向用户交付物品时平衡效果与效率。现有RS基准数据集主要关注曝光空间,新型RS算法在该空间中进行训练和评估。然而,当这些算法迁移到真实工业RS时,它们面临处理未曝光物品的关键挑战,而未曝光物品所在的空间远大于曝光空间。这种差异深刻影响其实际性能。此外,这些算法往往忽视多个RS阶段之间复杂的相互作用,导致整体系统性能次优。为解决这一问题,我们推出RecFlow,这是一个工业级全流程推荐数据集,旨在弥合离线RS基准与真实在线环境之间的差距。与现有数据集不同,RecFlow不仅包含来自曝光空间的样本,还包含在RS漏斗各阶段被过滤的未曝光物品。我们的数据集包含来自4.2万名用户、近900万个物品的3800万次交互,以及在37天内从930万个在线请求中收集的额外19亿条阶段样本,覆盖6个阶段。利用RecFlow数据集,我们开展了大胆的探索实验,展示了其在设计新算法方面的潜力,即通过纳入特定阶段样本来提升效果。其中部分算法已在线上部署,并持续带来显著收益。我们提出RecFlow作为RS社区首个综合基准数据集,支持研究任意阶段的算法设计、选择偏差研究、去偏算法、多阶段一致性与最优性、多任务推荐以及用户行为建模。RecFlow数据集及相应源代码可在https://github.com/RecFlow-ICLR/RecFlow获取。

英文摘要:

Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users. Existing RS benchmark datasets primarily focus on the exposure space, where novel RS algorithms are trained and evaluated. However, when these algorithms transition to real world industrial RS, they face a critical challenge of handling unexposed items which are a significantly larger space than the exposed one. This discrepancy profoundly impacts their practical performance. Additionally, these algorithms often overlook the intricate interplay between multiple RS stages, resulting in suboptimal overall system performance. To address this issue, we introduce RecFlow, an industrial full flow recommendation dataset designed to bridge the gap between offline RS benchmarks and the real online environment. Unlike existing datasets, RecFlow includes samples not only from the exposure space but also unexposed items filtered at each stage of the RS funnel. Our dataset comprises 38M interactions from 42K users across nearly 9M items with additional 1.9B stage samples collected from 9.3M online requests over 37 days and spanning 6 stages. Leveraging the RecFlow dataset, we conduct courageous exploration experiments, showcasing its potential in designing new algorithms to enhance effectiveness by incorporating stage-specific samples. Some of these algorithms have already been deployed online, consistently yielding significant gains. We propose RecFlow as the first comprehensive benchmark dataset for the RS community, supporting research on designing algorithms at any stage, study of selection bias, debiased algorithms, multi-stage consistency and optimality, multi-task recommendation, and user behavior modeling. The RecFlow dataset, along with the corresponding source code, is available at https://github.com/RecFlow-ICLR/RecFlow.

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。

↑