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.
翻译:重排序通过建模物品间的交互作用来提升推荐质量。然而,现有方法往往将排序与重排序解耦,导致在严格的延迟约束下,列表式评估模型因组合稀疏性和有限的表示能力而表现不佳。本文提出RIA(Ranking-Infused Architecture),一个统一、端到端的框架,无缝整合了点式与列表式评估。RIA包含四个关键组件:(1)用户与候选双Transformer(UCDT),用于细粒度的用户-物品-上下文建模;(2)上下文感知的用户历史与目标(CUHT)模块,用于位置敏感的偏好学习;(3)列表式多层级HSTU(LMH)模块,以捕捉分层的物品依赖关系;(4)嵌入缓存(EC)模块,在推理阶段桥接效率与效果。通过在排序和重排序间共享表示,RIA实现了丰富的上下文知识迁移,同时保持低延迟。大量实验表明,RIA在公开和工业数据集上均优于最先进的模型,在AUC和LogLoss指标上取得了显著提升。在美团广告系统中部署后,在线A/B测试显示,RIA使点击率(CTR)提升了+1.69%,千次展示成本(CPM)增加了+4.54%。