发表机构
LinkedIn Corporation（领英公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对领英信息流预排序延迟高、候选量大的问题，提出连接内容检索器，利用GPU排序搜索原语连接稠密图边特征与文档特征，实现50倍模型参数扩展和内容停留时间+2.5%的提升。
AI 中文摘要
在诸如领英信息流等大规模推荐系统中，由会员网络（好友关系和关注）生成的内容占据了超过70%的展示量和互动量。因此，预排序层必须将尽可能最佳的数百个候选内容转发给排序层，这一点至关重要。领英的职业知识图谱承载了跨越一度网络（好友关系和关注）和二度网络的互动信号：即一度好友关系用户曾点赞、评论或转发但并非其原创的帖子（即所谓的陌生人病毒式传播）。由于这种扇出效应，产生的候选索引超过十亿；从观看者网络中筛选活动可将其缩小至大约数万个活动，这些活动必须在120毫秒的p99延迟预算内完成评分。我们提出了连接内容检索器（CC Retriever），这是一个预排序系统，能够在GPU上以低延迟使用完整的深度排序模型对这些候选内容进行评分。其核心是一种排序搜索GPU原语，该原语在运行时将稠密图亲和特征（观看者到作者）与存储在GPU上的文档级特征在5-10毫秒内进行连接。转向GPU服务评分使得排序模型的参数规模扩大了50倍，并在在线实验中为领英信息流带来了内容停留时间+2.5%的提升，显著高于领英信息流实验中通常观察到的增益。在这项工作中，我们描述了从领英经济图谱中利用的特征集以及用于评分的模型架构，特别强调了扩展该技术栈的在线系统。
英文摘要
In large-scale recommendation systems like the LinkedIn Feed, content generated by a member's network (connections and follows) makes up over 70% of impressions and engagement. It is therefore essential that the pre-ranking layer forwards the best possible few hundred candidates to the ranking layer. LinkedIn's professional knowledge graph carries engagement signals across both the first degree network (connections and follows) and the second-degree network: posts that a 1st-degree connection reacted to, commented on or reshared but did not author (a.k.a. stranger viral). Due to this fan out, the resulting candidate index exceeds one billion; selection of activities from the viewer's network narrows it down to roughly tens of thousands of activities that must be scored within a 120 ms p99 latency budget. We present Connected Content Retriever (CC Retriever), a pre-ranking system that scores these candidates with a full deep ranking model on GPUs at low latency. At its core is a sorted-search GPU primitive that joins dense graph affinity features (viewer to author) with document level features stored on the GPU at runtime in 5-10 ms. The shift to GPU served scoring enabled a 50x scale up of the ranking model's parameters and delivered a +2.5% lift in content time spent on the LinkedIn Feed in online experiments, significantly higher than the typical gains observed in LinkedIn Feed experiments. In this work, we describe the feature set we leverage from LinkedIn's economic graph and the model architecture used for scoring, with a particular emphasis on the online system that scales the stack.
