提出CAPTS框架，优化多通道推荐中触发项的选择效率。
CAPTS: Channel-Aware, Preference-Aligned Trigger Selection for Multi-Channel Item-to-Item Retrieval
- 将多通道触发项选择建模为可学习的路由问题，统一优化流程。
- 引入前瞻反馈机制，按触发项后续带来的用户参与度评估其价值。
- 协调各通道间触发项分配，减少重复，提升整体推荐效果。
大规模工业推荐系统常采用多通道召回策略，结合用户到物品（U2I）直接召回与两跳用户-物品-物品（U2I2I）链路。在U2I2I中，系统从历史交互中选取少量行为作为触发项，用于启动跨多通道的物品到物品（I2I）召回。实际生产中，触发项通常通过规则策略或学习评分器逐通道独立筛选。然而，现有方法存在两大挑战：对触发项的价值评估偏倚，仅依据触发后的即时反馈而非其作为召回种子的长期效用；以及多通道路由不协调，各通道独立选触发表，导致跨通道重叠增加。为此，本文提出一种统一且灵活的框架——通道感知、偏好对齐的触发项选择（CAPTS），将多通道触发项选择视为可学习的路由问题。CAPTS引入价值归因模块（VAM），通过追溯每个触发项在各通道下所引发的后续互动表现，提供前瞻式监督信号；并设计通道自适应触发路由（CATR）模块，协同优化触发项与通道间的分配关系，最大化整体多通道召回价值。在快手国际版短视频平台Kwai上的大量离线实验与大规模在线A/B测试表明，CAPTS在离线场景中持续提升多通道召回率，并在线上实现单设备平均使用时长提升+0.351%。
原文摘要 · Abstract (English)
Large-scale industrial recommender systems commonly adopt multi-channel retrieval for candidate generation, combining direct user-to-item (U2I) retrieval with two-hop user-to-item-to-item (U2I2I) pipelines. In U2I2I, the system selects a small set of historical interactions as triggers to seed downstream item-to-item (I2I) retrieval across multiple channels. In production, triggers are often selected using rule-based policies or learned scorers and tuned in a channel-by-channel manner. However, these practices face two persistent challenges: biased value attribution that values triggers by on-trigger feedback rather than their downstream utility as retrieval seeds, and uncoordinated multi-channel routing where channels select triggers independently under a shared quota, increasing cross-channel overlap. To address these challenges, we propose Channel-Aware, Preference-Aligned Trigger Selection (CAPTS), a unified and flexible framework that treats multi-channel trigger selection as a learnable routing problem. CAPTS introduces a Value Attribution Module (VAM) that provides look-ahead supervision by crediting each trigger with the subsequent engagement generated by items retrieved from it on each I2I channel, and a Channel-Adaptive Trigger Routing (CATR) module that coordinates trigger-to-channel assignment to maximize the overall value of multi-channel retrieval. Extensive offline experiments and large-scale online A/B tests on Kwai, Kuaishou's international short-video platform, show that CAPTS consistently improves multi-channel recall offline and delivers a +0.351% lift in average time spent per device online.
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。