Achieving Low-Latency Graph-Based Vector Search via Aligning Best-First Search Algorithm with SSD
ACM Transactions on Storage · 31.05.2026 · 22 (2) · 1-30
DOI: 10.1145/3793926 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Storage, online erschienen am 26.03.2026. Verfasst von Hao Guo und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
We propose PipeANN , an on-disk graph-based approximate nearest neighbor search (ANNS) system, which significantly bridges the latency gap with in-memory ones. We achieve this by aligning the best-first search algorithm with SSD characteristics, avoiding strict compute-I/O order across search steps. Experiments show that PipeANN has 1.14×–2.02× search latency compared to in-memory Vamana, and 35.0% of the latency of on-disk DiskANN in billion-scale datasets, without sacrificing search accuracy. PipeANN is open-source at https://github.com/thustorage/PipeANN .
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Guo, H., & Lu, Y. (2026). Achieving Low-Latency Graph-Based Vector Search via Aligning Best-First Search Algorithm with SSD. ACM Transactions on Storage, 22(2), 1-30. https://doi.org/10.1145/3793926
Vancouver
Guo H, Lu Y. Achieving Low-Latency Graph-Based Vector Search via Aligning Best-First Search Algorithm with SSD. ACM Transactions on Storage. 2026;22(2):1-30. doi:10.1145/3793926
BibTeX
@article{Guo2026,
author = {Guo, Hao and Lu, Youyou},
title = {Achieving Low-Latency Graph-Based Vector Search via Aligning Best-First Search Algorithm with SSD},
journal = {ACM Transactions on Storage},
year = {2026},
volume = {22},
number = {2},
pages = {1--30},
doi = {10.1145/3793926}
}
EUVIMED