Meta用多个专用模型构建用户画像，提升推荐系统效果。
Mosaic: A Fleet of User Embedding Specialists for Recommendation at Meta
- 采用四类不同架构的专家模型分别捕捉用户行为不同方面。
- 新方法使离线指标显著提升，线上推荐效果也更好。
- 无需日志即可评估嵌入质量，加速开发迭代速度。
用户表征是工业级推荐系统中最具杠杆效应的建模问题：用户编码方式的一次改进可影响整个平台的召回、排序和安全任务。以往工业实践通常使用单一用户模型或共享主干+任务适配。本文提出Mosaic——一个基于专家舰队的用户建模范式，包含四类架构各异的模型家族：记忆驱动型、密集型、序列型与CoTrain模型，各自聚焦用户行为的不同维度。我们开发了多任务关系挖掘（MRM）和余弦冗余损失（CRL）技术，以最大化每个新专家的边际信息贡献。同时引入CoEval与用户塔置零（User Tower Zero-Out）等无日志嵌入评估框架，提升研发效率并保持下游任务对齐精度。混合CPU/GPU、在线/离线服务架构使每个专家可根据需求选择合适部署策略，兼顾实时性、延迟与计算开销。Mosaic在离线NE指标上实现持续显著提升，同时带来线上收益。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。