# Nearest neighbor search with compact codes: A decoder perspective

arXiv: https://arxiv.org/abs/2112.09568 · HTML: https://mlsanity.com/paper/2112.09568/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Spreading vectors for similarity search](https://mlsanity.com/paper/1806.03198/) (2018)
- [On Empirical Comparisons of Optimizers for Deep Learning](https://mlsanity.com/paper/1910.05446/) (2019)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)
- [Learning to Hash for Indexing Big Data - A Survey](https://mlsanity.com/paper/1509.05472/) (2015)
- [Hashing for Similarity Search: A Survey](https://mlsanity.com/paper/1408.2927/) (2014)
- [Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD](https://mlsanity.com/paper/1812.09162/) (2018)
- [Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search](https://mlsanity.com/paper/1509.05195/) (2015)

## Built on by (most cited first, 5 of 5)

- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Residual Quantization with Implicit Neural Codebooks](https://mlsanity.com/paper/2401.14732/) (2024)
- [OOD-DiskANN: Efficient and Scalable Graph ANNS for Out-of-Distribution Queries](https://mlsanity.com/paper/2211.12850/) (2022)
- [Machine learning and high dimensional vector search](https://mlsanity.com/paper/2502.16931/) (2025)
- [Vector search with small radiuses](https://mlsanity.com/paper/2403.10746/) (2024)

## Abstract (arXiv)

Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization. These methods minimize a certain loss, typically the mean squared error or other objective functions tailored to the retrieval problem. In this paper, we re-interpret popular methods such as binary hashing or product quantizers as auto-encoders, and point out that they implicitly make suboptimal assumptions on the form of the decoder. We design backward-compatible decoders that improve the reconstruction of the vectors from the same codes, which translates to a better performance in nearest neighbor search. Our method significantly improves over binary hashing methods or product quantization on popular benchmarks.