AI 中文总结
研究工业推荐系统中用户表示问题，提出 Mosaic 平台，用四个不同模型家族组成的专家集群学习用户嵌入，开发 MRM 和 CRL 技术，引入新评估框架，其服务栈灵活，带来离线和在线收益。
AI 中文摘要
用户表示是工业推荐系统中最具影响力的建模问题之一：用户编码方式的每一项进展都能在平台规模上的检索、排序和完整性任务中传播。先前的工业用户表示工作要么构建一个发出一个或多个嵌入向量的单一用户模型，要么构建一个带有特定任务适配的共享主干。本文提出了 Mosaic，一个基础用户建模平台，它采用一群专家来学习用户嵌入。该集群由四个架构不同的模型家族组成，每个家族专注于用户行为的一个不同方面。我们开发了 MRM 和 CRL 技术以最大化每个新专家的边际信息贡献。我们还引入了 CoEval 和 User Tower Zero-Out，这是新的无日志嵌入评估框架，可提高开发速度同时保持与下游对齐的准确性。我们的混合 CPU/GPU、在线和离线服务栈允许每个专家选择合适的服务策略以满足新鲜度、延迟和计算要求。Mosaic 除了在线收益外，还带来了一致且显著的离线 NE 改进。
英文摘要
User representation is one of the highest-leverage modeling problems in industrial recommendation systems: a single advancement in how users are encoded can propagate across retrieval, ranking, and integrity tasks at platform scale. Prior industrial user representation work builds either a single user model that emits one or more embedding vectors or a shared backbone with task-specific adaptation. In this paper, we present Mosaic, a foundational user modeling platform that employs a fleet of specialists to learn user embeddings. The fleet comprises four architecturally diverse model families - memorization-driven, dense-heavy, sequential-based, and CoTrain models - each focusing on a distinct facet of user behavior. We developed MRM (Multi-task Relations Mining) and CRL (Cosine Redundancy Loss) techniques to maximize the marginal information contribution of each new specialist. We also introduce CoEval and User Tower Zero-Out, new logging-free embedding evaluation framework that improves development velocity while preserving downstream-aligned accuracy. Our hybrid CPU/GPU, online-and-offline serving stack allows each specialist to choose the adequate serving strategy to meet the freshness, latency, and computational requirements. Mosaic delivers consistent and significant offline NE improvements in addition to online gains.
CommentsAccepted in the 20th ACM Conference on Recommender Systems (RecSys '26),
