CoChat

Survey of vector database management systems

Open access
Pan, James Jie, Wang, Jianguo, Li, Guoliang · 2024 · The VLDB Journal
Cited by 173

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s00778-024-00864-x

Cites

14 of 14 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Cited by

See all 173

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.