提出统一框架RIA，提升推荐列表点击率预测精度与效率。
RIA: A Ranking-Infused Approach for Optimized listwise CTR Prediction
- 融合点对点与列表级评估，共享表征实现端到端优化。
- 在美团广告系统中点击率提升1.69%，千次展示成本增4.54%。
- 适合追求高精度与低延迟的工业级推荐系统应用。
重排序通过建模物品间交互提升推荐质量，但现有方法常将排序与重排序解耦，导致列表级评估模型在严格延迟约束下存在组合稀疏性与表征能力不足问题。本文提出RIA（排名融合架构），一种统一的端到端框架，无缝集成点对点与列表级评估。RIA引入四大组件：(1) 用户与候选双变压器（UCDT）用于细粒度用户-物品-上下文建模；(2) 上下文感知的用户历史与目标模块（CUHT）实现位置敏感偏好学习；(3) 列表级多层级状态转移单元（LMH）捕捉物品层级依赖；(4) 嵌入缓存（EC）模块在推理中平衡效率与效果。通过共享排序与重排序间的表示，RIA实现丰富上下文知识迁移并保持低延迟。大量实验表明，RIA在公开与工业数据集上均优于现有最优模型，在AUC与LogLoss上取得显著提升。部署于美团广告系统，在线上A/B测试中实现点击率提升1.69%，千次展示成本增加4.54%。
原文摘要 · Abstract (English)
Reranking improves recommendation quality by modeling item interactions. However, existing methods often decouple ranking and reranking, leading to weak listwise evaluation models that suffer from combinatorial sparsity and limited representational power under strict latency constraints. In this paper, we propose RIA (Ranking-Infused Architecture), a unified, end-to-end framework that seamlessly integrates pointwise and listwise evaluation. RIA introduces four key components: (1) the User and Candidate DualTransformer (UCDT) for fine-grained user-item-context modeling; (2) the Context-aware User History and Target (CUHT) module for position-sensitive preference learning; (3) the Listwise Multi-HSTU (LMH) module to capture hierarchical item dependencies; and (4) the Embedding Cache (EC) module to bridge efficiency and effectiveness during inference. By sharing representations across ranking and reranking, RIA enables rich contextual knowledge transfer while maintaining low latency. Extensive experiments show that RIA outperforms state-of-the-art models on both public and industrial datasets, achieving significant gains in AUC and LogLoss. Deployed in Meituan advertising system, RIA yields a +1.69% improvement in Click-Through Rate (CTR) and a +4.54% increase in Cost Per Mille (CPM) in online A/B tests.
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。