Meta redesigns model空间，实现广告推荐成本与效果双赢。
Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations
- 重构模型空间，跨域共享知识并统一模型结构
- 上线后收入指标提升10%，转化率增6%，用户满意度升11.5%
- 适合关注工业级推荐系统降本增效的工程师与研究者
产品、平台、政策和法规的快速演进给在工业规模部署先进推荐模型带来挑战，主要源于跨领域数据碎片化及不断上升的基础设施成本，阻碍了持续的质量提升。为此，我们提出Lattice，一种以模型空间重设计为核心的推荐框架，将多域多目标（MDMO）学习从模型和学习目标层面拓展至整体架构。Lattice通过跨域知识共享、数据整合、模型统一、模型压缩与系统优化，显著提升质量与成本效率。在Meta的部署中，实现10%的收入驱动型核心指标增长，用户满意度提升11.5%，转化率提高6%，同时节省20%计算资源容量。
原文摘要 · Abstract (English)
The rapidly evolving landscape of products, surfaces, policies, and regulations poses significant challenges for deploying state-of-the-art recommendation models at industry scale, primarily due to data fragmentation across domains and escalating infrastructure costs that hinder sustained quality improvements. To address this challenge, we propose Lattice, a recommendation framework centered around model space redesign that extends Multi-Domain, Multi-Objective (MDMO) learning beyond models and learning objectives. Lattice addresses these challenges through a comprehensive model space redesign that combines cross-domain knowledge sharing, data consolidation, model unification, distillation, and system optimizations to achieve significant improvements in both quality and cost-efficiency. Our deployment of Lattice at Meta has resulted in 10% revenue-driving top-line metrics gain, 11.5% user satisfaction improvement, 6% boost in conversion rate, with 20% capacity saving.
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。