# Binary Embedding-based Retrieval at Tencent

arXiv: https://arxiv.org/abs/2302.08714 · HTML: https://mlsanity.com/paper/2302.08714/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph](https://mlsanity.com/paper/1707.00143/) (2017)
- [Towards Backward-Compatible Representation Learning](https://mlsanity.com/paper/2003.11942/) (2020)
- [Feature Learning based Deep Supervised Hashing with Pairwise Labels](https://mlsanity.com/paper/1511.03855/) (2015)
- [Semantic Models for the First-stage Retrieval: A Comprehensive Review](https://mlsanity.com/paper/2103.04831/) (2021)
- [Semantic Product Search](https://mlsanity.com/paper/1907.00937/) (2019)
- [Embedding-based Product Retrieval in Taobao Search](https://mlsanity.com/paper/2106.09297/) (2021)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning](https://mlsanity.com/paper/2006.02282/) (2020)
- [Unified Representation Learning for Cross Model Compatibility](https://mlsanity.com/paper/2008.04821/) (2020)
- [Asymmetric metric learning for knowledge transfer](https://mlsanity.com/paper/2006.16331/) (2020)
- [Deep Supervised Hashing with Triplet Labels](https://mlsanity.com/paper/1612.03900/) (2016)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation](https://mlsanity.com/paper/2103.13506/) (2021)
- [Deep Triplet Quantization](https://mlsanity.com/paper/1902.00153/) (2019)
- [Learning Backward Compatible Embeddings](https://mlsanity.com/paper/2206.03040/) (2022)
- [Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD](https://mlsanity.com/paper/1812.09162/) (2018)
- [Accelerated Nearest Neighbor Search with Quick ADC](https://mlsanity.com/paper/1704.07355/) (2017)
- [Bolt: Accelerated Data Mining with Fast Vector Compression](https://mlsanity.com/paper/1706.10283/) (2017)
- [Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval](https://mlsanity.com/paper/2201.09724/) (2022)

## Built on by (most cited first, 6 of 6)

- [To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering](https://mlsanity.com/paper/2403.01924/) (2024)
- [MicroNN: An On-device Disk-resident Updatable Vector Database](https://mlsanity.com/paper/2504.05573/) (2025)
- [REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing](https://mlsanity.com/paper/2506.16444/) (2025)
- [Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems](https://mlsanity.com/paper/2409.14682/) (2024)
- [When Embedding Models Meet: Procrustes Bounds and Applications](https://mlsanity.com/paper/2510.13406/) (2025)
- [Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval](https://mlsanity.com/paper/2609.07276/) (2026)

## Abstract (arXiv)

Large-scale embedding-based retrieval (EBR) is the cornerstone of search-related industrial applications. Given a user query, the system of EBR aims to identify relevant information from a large corpus of documents that may be tens or hundreds of billions in size. The storage and computation turn out to be expensive and inefficient with massive documents and high concurrent queries, making it difficult to further scale up. To tackle the challenge, we propose a binary embedding-based retrieval (BEBR) engine equipped with a recurrent binarization algorithm that enables customized bits per dimension. Specifically, we compress the full-precision query and document embeddings, formulated as float vectors in general, into a composition of multiple binary vectors using a lightweight transformation model with residual multilayer perception (MLP) blocks. We can therefore tailor the number of bits for different applications to trade off accuracy loss and cost savings. Importantly, we enable task-agnostic efficient training of the binarization model using a new embedding-to-embedding strategy. We also exploit the compatible training of binary embeddings so that the BEBR engine can support indexing among multiple embedding versions within a unified system. To further realize efficient search, we propose Symmetric Distance Calculation (SDC) to achieve lower response time than Hamming codes. We successfully employed the introduced BEBR to Tencent products, including Sogou, Tencent Video, QQ World, etc. The binarization algorithm can be seamlessly generalized to various tasks with multiple modalities. Extensive experiments on offline benchmarks and online A/B tests demonstrate the efficiency and effectiveness of our method, significantly saving 30%~50% index costs with almost no loss of accuracy at the system level.