解决首页推荐中的虚假负样本问题，提升点击率35.4%。
USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations
- 基于用户意图筛选无效曝光样本，避免误判不点击为不喜欢。
- 联合修正曝光偏倚与点击偏倚，显著提升推荐精准度。
- 适用于电商首页推荐场景，尤其适合营销区块优化。
大规模首页推荐面临由曝光偏倚导致的伪负样本问题，即用户未点击可能源于注意力不足而非真实反感。现有方法缺乏对无效曝光的深入分析，且多仅关注单一环节（如采样策略），忽视了伪正样本的影响——例如用户点击首页仅为访问营销页面。为此，我们提出一个统一的采样与双去偏框架。其包含两个核心组件：(1) 用户意图感知的负样本采样模块，用于过滤无效曝光样本；(2) 意图驱动的双去偏模块，协同纠正曝光偏倚与点击偏倚。在淘宝首页的大量线上实验表明，该框架在两个营销区块（百依不贴、淘秒杀）上分别实现用户点击率（UCTR）提升35.4%和14.5%。
原文摘要 · Abstract (English)
Large-scale homepage recommendations face critical challenges from pseudo-negative samples caused by exposure bias, where non-clicks may indicate inattention rather than disinterest. Existing work lacks thorough analysis of invalid exposures and typically addresses isolated aspects (e.g., sampling strategies), overlooking the critical impact of pseudo-positive samples - such as homepage clicks merely to visit marketing portals. We propose a unified framework for large-scale homepage recommendation sampling and debiasing. Our framework consists of two key components: (1) a user intent-aware negative sampling module to filter invalid exposure samples, and (2) an intent-driven dual-debiasing module that jointly corrects exposure bias and click bias. Extensive online experiments on Taobao demonstrate the efficacy of our framework, achieving significant improvements in user click-through rates (UCTR) by 35.4% and 14.5% in two variants of the marketing block on the Taobao homepage, Baiyibutie and Taobaomiaosha.
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。