用离线预排序提升推荐召回率，线上推理无需计算
RADAR: Recall Augmentation through Deferred Asynchronous Retrieval
- 离线用强模型预排海量候选，存为高质量检索源
- 线上直接调用预排结果，召回率提升至基线2倍
- 适合高并发场景下优化推荐质量的工程团队
现代大规模推荐系统采用多阶段排序流程（检索、预排、排序）以平衡用户参与度与计算约束（延迟、CPU）。然而，初始检索阶段通常依赖高效但精度较低的方法（如KNN），难以从百亿级商品库中有效识别最具吸引力的物品，尤其难以区分高度相关且吸引人的候选与仅相关者。本文提出一种新框架RADAR（通过延迟异步检索实现召回增强），利用异步离线计算，使用完整复杂度的排序模型对用户预排更大规模候选集。这些排名靠前的项目被存储并作为线上推理时的高质量检索来源，从而跳过在线检索和预排阶段。离线实验表明，RADAR显著提升召回率（在@200指标上达基线DNN检索的2倍）。线上A/B测试验证了拓扑参与度指标提升0.8%，证明RADAR是在严格线上服务约束下提升推荐质量的有效实用方法。
原文摘要 · Abstract (English)
Modern large-scale recommender systems employ multi-stage ranking funnel (Retrieval, Pre-ranking, Ranking) to balance engagement and computational constraints (latency, CPU). However, the initial retrieval stage, often relying on efficient but less precise methods like K-Nearest Neighbors (KNN), struggles to effectively surface the most engaging items from billion-scale catalogs, particularly distinguishing highly relevant and engaging candidates from merely relevant ones. We introduce Recall Augmentation through Deferred Asynchronous Retrieval (RADAR), a novel framework that leverages asynchronous, offline computation to pre-rank a significantly larger candidate set for users using the full complexity ranking model. These top-ranked items are stored and utilized as a high-quality retrieval source during online inference, bypassing online retrieval and pre-ranking stages for these candidates. We demonstrate through offline experiments that RADAR significantly boosts recall (2X Recall@200 vs DNN retrieval baseline) by effectively combining a larger retrieved candidate set with a more powerful ranking model. Online A/B tests confirm a +0.8% lift in topline engagement metrics, validating RADAR as a practical and effective method to improve recommendation quality under strict online serving constraints.
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。