提升大规模召回系统负样本质量，减少误判并降低计算成本
ESANS: Effective and Semantic-Aware Negative Sampling for Large-Scale Retrieval Systems
- 通过低维空间插值生成虚拟负样本，提升采样多样性与密度
- 基于多模态信息分层聚类，增强负样本语义一致性，减少误判
- 适合工业级推荐系统，兼顾性能与效率，可直接部署于线上
工业推荐系统通常采用两阶段流程：召回与排序，旨在将用户与数百万项物品匹配。在召回阶段，经典的基于嵌入的召回（EBR）方法依赖高效的负样本采样技术来提升性能与效率。然而，现有技术常面临误判负样本、保障采样质量成本高以及语义信息不足的问题。为此，本文提出有效且语义感知的负样本采样方法（ESANS），包含两个核心组件：有效密集插值策略（EDIS）和多模态语义感知聚类（MSAC）。EDIS在低维嵌入空间内生成虚拟样本，提升采样分布的多样性和密度，同时最小化计算开销。MSAC基于视觉、文本和行为等多模态信息对物品表示进行分层聚类，确保负样本的语义一致性，减少误判。大量离线与在线实验验证了ESANS在效率与性能上的优越性。
原文摘要 · Abstract (English)
Industrial recommendation systems typically involve a two-stage process: retrieval and ranking, which aims to match users with millions of items. In the retrieval stage, classic embedding-based retrieval (EBR) methods depend on effective negative sampling techniques to enhance both performance and efficiency. However, existing techniques often suffer from false negatives, high cost for ensuring sampling quality and semantic information deficiency. To address these limitations, we propose Effective and Semantic-Aware Negative Sampling (ESANS), which integrates two key components: Effective Dense Interpolation Strategy (EDIS) and Multimodal Semantic-Aware Clustering (MSAC). EDIS generates virtual samples within the low-dimensional embedding space to improve the diversity and density of the sampling distribution while minimizing computational costs. MSAC refines the negative sampling distribution by hierarchically clustering item representations based on multimodal information (visual, textual, behavioral), ensuring semantic consistency and reducing false negatives. Extensive offline and online experiments demonstrate the superior efficiency and performance of ESANS.
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。