# Vector and Line Quantization for Billion-scale Similarity Search on GPUs

arXiv: https://arxiv.org/abs/1901.00275 · HTML: https://mlsanity.com/paper/1901.00275/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2019.

## Built on by (most cited first, 3 of 3)

- [Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models](https://mlsanity.com/paper/2310.09949/) (2023)
- [Co-design Hardware and Algorithm for Vector Search](https://mlsanity.com/paper/2306.11182/) (2023)
- [A Semantic Indexing Structure for Image Retrieval](https://mlsanity.com/paper/2109.06583/) (2021)

## Abstract (arXiv)

Billion-scale high-dimensional approximate nearest neighbour (ANN) search has become an important problem for searching similar objects among the vast amount of images and videos available online. The existing ANN methods are usually characterized by their specific indexing structures, including the inverted index and the inverted multi-index structure. The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs. However, the inverted index requires high memory overhead to index the dataset effectively. The inverted multi-index structure is difficult to implement for GPUs, and also ineffective in dealing with database with different data distributions. In this paper we propose a novel hierarchical inverted index structure generated by vector and line quantization methods. Our quantization method improves both search efficiency and accuracy, while maintaining comparable memory consumption. This is achieved by reducing search space and increasing the number of indexed regions. We introduce a new ANN search system, VLQ-ADC, that is based on the proposed inverted index, and perform extensive evaluation on two public billion-scale benchmark datasets SIFT1B and DEEP1B. Our evaluation shows that VLQ-ADC significantly outperforms the state-of-the-art GPU- and CPU-based systems in terms of both accuracy and search speed. The source code of VLQ-ADC is available at https://github.com/zjuchenwei/vector-line-quantization.