EUVIMEDEUVIMED entdecken
Crossref

VSAG: An Optimized Search Framework for Graph-Based Approximate Nearest Neighbor Search

Xiaoyao Zhong, Haotian Li, Jiabao Jin, Mingyu Yang, Deming Chu, Xiangyu Wang, Zhitao Shen, Wei Jia, George Gu, Yi Xie, Xuemin Lin, Heng Tao Shen und 2 weitere

Proceedings of the VLDB Endowment · 2025-08 · 18 (12) · 5017-5030

DOI: 10.14778/3750601.3750624 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 16.09.2025. Verfasst von Xiaoyao Zhong und 13 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 62 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Approximate nearest neighbor search (ANNS) is a fundamental problem in vector databases and AI infrastructures. Recent graph-based ANNS algorithms have achieved high search accuracy with practical efficiency. Despite the advancements, these algorithms still face performance bottlenecks in production, due to the random memory access patterns of graph-based search and the high computational overheads of vector distance. In addition, the performance of a graph-based ANNS algorithm is highly sensitive to parameters, while selecting the optimal parameters is cost-prohibitive, e.g., manual tuning requires repeatedly re-building the index. This paper introduces VSAG , an open-source framework that aims to enhance the in production performance of graph-based ANNS algorithms. VSAG has been deployed at scale in the services of Ant Group, and it incorporates three key optimizations: ( i) efficient memory access : it reduces L3 cache misses with pre-fetching and cache-friendly vector organization; ( ii) automated parameter tuning : it automatically selects performance-optimal parameters without requiring index rebuilding; ( iii) efficient distance computation : it leverages modern hardware, scalar quantization, and smartly switches to low-precision representation to dramatically reduce the distance computation costs. We evaluate VSAG on real-world datasets. The experimental results show that VSAG achieves the state-of-the-art performance and provides up to 4× speedup over HNSWlib (an industry-standard library) while ensuring the same accuracy.

Zitieren

APA

Zhong, X., Li, H., Jin, J., Yang, M., Chu, D., Wang, X., Shen, Z., Jia, W., Gu, G., Xie, Y., Lin, X., Shen, H. T., Song, J., & Cheng, P. (2025). VSAG: An Optimized Search Framework for Graph-Based Approximate Nearest Neighbor Search. Proceedings of the VLDB Endowment, 18(12), 5017-5030. https://doi.org/10.14778/3750601.3750624

Vancouver

Zhong X, Li H, Jin J, Yang M, Chu D, Wang X, et al. VSAG: An Optimized Search Framework for Graph-Based Approximate Nearest Neighbor Search. Proceedings of the VLDB Endowment. 2025;18(12):5017-5030. doi:10.14778/3750601.3750624

BibTeX
@article{Zhong2025,
  author = {Zhong, Xiaoyao and Li, Haotian and Jin, Jiabao and Yang, Mingyu and Chu, Deming and Wang, Xiangyu and Shen, Zhitao and Jia, Wei and Gu, George and Xie, Yi and Lin, Xuemin and Shen, Heng Tao and Song, Jingkuan and Cheng, Peng},
  title = {VSAG: An Optimized Search Framework for Graph-Based Approximate Nearest Neighbor Search},
  journal = {Proceedings of the VLDB Endowment},
  year = {2025},
  volume = {18},
  number = {12},
  pages = {5017--5030},
  doi = {10.14778/3750601.3750624}
}
Kostenlos starten →