ESANS: Effective and Semantic-Aware Negative Sampling for Large-Scale Retrieval Systems

Abstract

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.

10 pages, 6 figures, Proceedings of the ACM Web Conference 2025

References in corpus (5)

• Ask the GRU: Multi-Task Learning for Deep Text Recommendations
• Embedding-based Retrieval in Facebook Search
• ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance
• Learning Latent Vector Spaces for Product Search
• Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation