# Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

arXiv: https://arxiv.org/abs/2201.05409 · HTML: https://mlsanity.com/paper/2201.05409/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 14 Jan 2022.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [Pre-training Tasks for Embedding-based Large-scale Retrieval](https://mlsanity.com/paper/2002.03932/) (2020)
- [Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph](https://mlsanity.com/paper/1707.00143/) (2017)
- [An Unsupervised Sentence Embedding Method by Mutual Information Maximization](https://mlsanity.com/paper/2009.12061/) (2020)
- [Efficient Passage Retrieval with Hashing for Open-domain Question Answering](https://mlsanity.com/paper/2106.00882/) (2021)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search](https://mlsanity.com/paper/2105.09613/) (2021)
- [Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors](https://mlsanity.com/paper/1802.02422/) (2018)
- [Differentiable Product Quantization for End-to-End Embedding Compression](https://mlsanity.com/paper/1908.09756/) (2019)
- [Pre-trained Language Model for Web-scale Retrieval in Baidu Search](https://mlsanity.com/paper/2106.03373/) (2021)

## Built on by (most cited first, 7 of 7)

- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings](https://mlsanity.com/paper/2204.00185/) (2022)
- [RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models](https://mlsanity.com/paper/2305.02564/) (2023)
- [FIT-RAG: Black-Box RAG with Factual Information and Token Reduction](https://mlsanity.com/paper/2403.14374/) (2024)
- [SeDR: Segment Representation Learning for Long Documents Dense Retrieval](https://mlsanity.com/paper/2211.10841/) (2022)
- [UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers](https://mlsanity.com/paper/2410.20163/) (2024)
- [GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishou](https://mlsanity.com/paper/2507.15267/) (2025)

## Abstract (arXiv)

Ad-hoc search calls for the selection of appropriate answers from a massive-scale corpus. Nowadays, the embedding-based retrieval (EBR) becomes a promising solution, where deep learning based document representation and ANN search techniques are allied to handle this task. However, a major challenge is that the ANN index can be too large to fit into memory, given the considerable size of answer corpus. In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification. For the best of retrieval accuracy, a Progressive Optimization framework is designed. The sparse embeddings are learned ahead for high-quality search of candidates. Conditioned on the candidate distribution induced by the sparse embeddings, the dense embeddings are continuously learned to optimize the discrimination of ground-truth from the shortlisted candidates. Besides, two techniques: the contrastive quantization and the locality-centric sampling are introduced for the learning of sparse and dense embeddings, which substantially contribute to their performances. Thanks to the above features, our method effectively handles massive-scale EBR with strong advantages in accuracy: with up to +4.3% recall gain on million-scale corpus, and up to +17.5% recall gain on billion-scale corpus. Besides, Our method is applied to a major sponsored search platform with substantial gains on revenue (+1.95%), Recall (+1.01%) and CTR (+0.49%). Our code is available at https://github.com/microsoft/BiDR.