# Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

arXiv: https://arxiv.org/abs/2205.03284 · HTML: https://mlsanity.com/paper/2205.03284/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2022.

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

- [Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval](https://mlsanity.com/paper/2312.15503/) (2023)
- [ESPN: Memory-Efficient Multi-Vector Information Retrieval](https://mlsanity.com/paper/2312.05417/) (2023)
- [PCA-RAG: Principal Component Analysis for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08386/) (2025)
- [Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks](https://mlsanity.com/paper/2602.06526/) (2026)
- [Spectral Tempering for Embedding Compression in Dense Passage Retrieval](https://mlsanity.com/paper/2603.19339/) (2026)
- [Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability](https://mlsanity.com/paper/2608.11238/) (2026)

## Abstract (arXiv)

Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers. However, these high-dimensional embeddings lead to larger index storage and higher retrieval latency. To reduce the embedding dimensions of dense retrieval, this paper proposes a Conditional Autoencoder (ConAE) to compress the high-dimensional embeddings to maintain the same embedding distribution and better recover the ranking features. Our experiments show that ConAE is effective in compressing embeddings by achieving comparable ranking performance with its teacher model and making the retrieval system more efficient. Our further analyses show that ConAE can alleviate the redundancy of the embeddings of dense retrieval with only one linear layer. All codes of this work are available at https://github.com/NEUIR/ConAE.