# Learning Multi-Stage Multi-Grained Semantic Embeddings for E-Commerce Search

arXiv: https://arxiv.org/abs/2303.11009 · HTML: https://mlsanity.com/paper/2303.11009/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2023.

## Built on by (most cited first, 9 of 9)

- [Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval](https://mlsanity.com/paper/2407.21488/) (2024)
- [Database-Augmented Query Representation for Information Retrieval](https://mlsanity.com/paper/2406.16013/) (2024)
- [Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model](https://mlsanity.com/paper/2405.05606/) (2024)
- [Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models](https://mlsanity.com/paper/2505.07105/) (2025)
- [A Scalable and Efficient Signal Integration System for Job Matching](https://mlsanity.com/paper/2507.09797/) (2025)
- [CardRewriter: Leveraging Knowledge Cards for Long-Tail Query Rewriting on Short-Video Platforms](https://mlsanity.com/paper/2510.10095/) (2025)
- [pEBR: A Probabilistic Approach to Embedding Based Retrieval](https://mlsanity.com/paper/2410.19349/) (2024)
- [Beyond Retrieval-Ranking: A Multi-Agent Cognitive Decision Framework for E-Commerce Search](https://mlsanity.com/paper/2510.20567/) (2025)
- [When & How to Write for Personalized Demand-aware Query Rewriting in Video Search](https://mlsanity.com/paper/2602.17667/) (2025)

## Abstract (arXiv)

Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework to learn embedding vectors for query and item separately and thus leverage efficient approximate nearest neighbor (ANN) search to retrieve relevant items. However, existing EBR methods usually ignore inconsistent user behaviors in industrial multi-stage search systems, resulting in insufficient retrieval efficiency with a low commercial return. To tackle this challenge, we propose to improve EBR methods by learning Multi-level Multi-Grained Semantic Embeddings(MMSE). We propose the multi-stage information mining to exploit the ordered, clicked, unclicked and random sampled items in practical user behavior data, and then capture query-item similarity via a post-fusion strategy. We then propose multi-grained learning objectives that integrate the retrieval loss with global comparison ability and the ranking loss with local comparison ability to generate semantic embeddings. Both experiments on a real-world billion-scale dataset and online A/B tests verify the effectiveness of MMSE in achieving significant performance improvements on metrics such as offline recall and online conversion rate (CVR).