Survey of vector database management systems
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
There are now over 20 commercial vector database management systems (VDBMSs), all produced within the past five years. But embedding-based retrieval has been studied for over ten years, and similarity search a staggering half century and more. Driving this shift from algorithms to systems are new data intensive applications, notably large language models, that demand vast stores of unstructured data coupled with reliable, secure, fast, and scalable query processing capability. A variety of new data management techniques now exist for addressing these needs, however there is no comprehensive survey to thoroughly review these techniques and systems. We start by identifying five main obstacles to vector data management, namely the ambiguity of semantic similarity, large size of vectors, high cost of similarity comparison, lack of structural properties that can be used for indexing, and difficulty of efficiently answering “hybrid” queries that jointly search both attributes and vectors. Overcoming these obstacles has led to new approaches to query processing, storage and indexing, and query optimization and execution. For query processing, a variety of similarity scores and query types are now well understood; for storage and indexing, techniques include vector compression, namely quantization, and partitioning techniques based on randomization, learned partitioning, and “navigable” partitioning; for query optimization and execution, we describe new operators for hybrid queries, as well as techniques for plan enumeration, plan selection, distributed query processing, data manipulation queries, and hardware accelerated query execution. These techniques lead to a variety of VDBMSs across a spectrum of design and runtime characteristics, including “native” systems that are specialized for vectors and “extended” systems that incorporate vector capabilities into existing systems. We then discuss benchmarks, and finally outline research challenges and point the direction for future work.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Collective dynamics of ‘small-world’ networks
Watts, D. J., & Strogatz, S. H. (1998) · Nature · doi:10.1038/30918 · Cited by 43,060
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 3×
“These queries may aim to return exact or approximate nearest neighbors, and may also specify the number of neighbors to return.”
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Approximate nearest neighbors: towards removing the curse of dimensionality
Indyk, P., & Motwani, R. (1998) · Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98 · doi:10.1145/276698.276876 · Cited by 4,188
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140 · cited 3×
“In [136], the distance function used for edge traversal is augmented with an attribute related component so that the scan favors nodes that are likely to pass the filter 20 .”
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 5×
“To address the difficulty of partitioning vector collections, techniques include randomization [67,49,31, 96,48,52,123,115], learned partitioning [127,69,91,96, 112], and what we refer to as “navigable” partitioning [51,89,90].”
BackgroundMethodInfluentialWhen Is ''Nearest Neighbor'' Meaningful?
Beyer, K., Goldstein, J., Ramakrishnan, R., & Shaft, U. (1999) · Lecture Notes in Computer Science · doi:10.1007/3-540-49257-7_15 · Cited by 2,403 · cited 1×
“Finding M is one of the goals of metric learning , and we point interested readers to [121] for a survey of techniques.”
Malkov, Y. A., & Yashunin, D. A. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889473 · Cited by 1,904
Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions
Andoni, A., & Indyk, P. (2008) · Communications of the ACM · doi:10.1145/1327452.1327494 · Cited by 1,437 · cited 1×
“The exact value depends on the accuracy and performance needs of the application, and some sample curves are shown in [30].”
Background(1993) · doi:10.5555/313559.313789 · Cited by 998
(2021) · doi:10.1145/3448016.3457550 · Cited by 416
Self-citationRetrieval-based Language Models and Applications
Asai, A., Min, S., Zhong, Z., & Chen, D. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts) · doi:10.18653/v1/2023.acl-tutorials.6 · Cited by 81
Bang, F. (2023) · Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023) · doi:10.18653/v1/2023.nlposs-1.24 · Cited by 72
Cited by
AI agents under threat: A survey of key security challenges and future pathways
Deng, Z., Guo, Y., Han, C., Ma, W., Xiong, J., Wen, S., & Xiang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3716628 · Cited by 210
When Large Language Models Meet Vector Databases: A Survey
Jing, Z., Su, Y., & Han, Y. (2025) · 2025 Conference on Artificial Intelligence x Multimedia (AIxMM) · doi:10.1109/aixmm62960.2025.00008 · Cited by 93
GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications
Sun, J., Li, G., Pan, J., Wang, J., Xie, Y., Liu, R., & Nie, W. (2025) · Proceedings of the VLDB Endowment · doi:10.14778/3750601.3750619 · Cited by 13
Self-citationLanguage-Models-as-a-Service: Overview of a New Paradigm and its Challenges
La Malfa, E., Petrov, A., Frieder, S., Weinhuber, C., Burnell, R., Nazar, R., Cohn, A., Shadbolt, N., & Wooldridge, M. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15865 · Cited by 9
Data Organisation for Efficient Pattern Retrieval: Indexing, Storage, and Access Structures
Koukaras, P., & Tjortjis, C. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9100258 · Cited by 3
Metadata
- Authors
- Pan, J. J., Wang, J., & Li, G.
- Venue
- The VLDB Journal
- Published
- 2024-07-15
- Volume
- 33
- Issue
- 5
- Pages
- 1591-1615
- ISSN
- 0949-877X (ISSN-L)
- 1066-8888
- OpenAlex
- W4400641571
- Cited by
- 173
- References
- 14
- FWCI
- 29.33
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.