CoChat
Sign Up
Cited by 1,008Advanced Image and Video Retrieval TechniquesTopic ModelingAdvanced Database Systems and Queries

The DOI matches its Crossref record, with a small difference in title or year; 62 of the 62 references it cites were found in a registry or an index.

The Faiss Library

Open access
Douze, Matthijs, Guzhva, Alexandr, Deng, Chengqi, Johnson, Jeff, Szilvasy, Gergely, Mazaré, Pierre-Emmanuel, Lomeli, Maria, Hosseini, Lucas, Jégou, Hervé·2026·IEEE Transactions on Big Data
DOI 10.1109/tbdata.2025.3618474
Open this paper in CoChat — free account

Abstract

Vector databases typically manage large collections of embedding vectors. As AI applications are growing rapidly, the number of embeddings that need to be stored and indexed is increasing. The Faiss library is dedicated to vector similarity search, a core functionality of vector databases. Faiss is a toolkit of indexing methods and related primitives used to search, cluster, compress and transform vectors. This paper describes the trade-offs in vector search and the design principles of Faiss in terms of structure, approach to optimization and interfacing. We benchmark key features of the library and discuss a few selected use cases to highlight its broad applicability.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/tbdata.2025.3618474

Cites

62 of 62 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Flagged first, then by citations

Show all 61 references

Research works printed but not linked: 15

  1. Paterek, Improving regularized singular value decomposition for collaborative filtering, 5
  2. Radford, Learning transferable visual models from natural language supervision, 8748
  3. 10.5555/3524938.3525087 · DOI
  4. Matsui, 2018, A survey of product quantization, ITE Trans. Media Technol. Appl., 16, 2
  5. Guo, Accelerating large-scale inference with anisotropic vector quantization, 3887
  6. Subramanya, DiskANN: Fast accurate billion-point nearest neighbor search on a single node, 13766
  7. Simhadri, 2022, Results of the NeurIPS’21 challenge on billion-scale approximate nearest neighbor search, 176, 177
  8. Babenko, Efficient indexing of billion-scale datasets of deep descriptors, 2055
  9. Morozov, Non-metric similarity graphs for maximum inner product search, 4726
  10. Weber, 1998, A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces, VLDB, 98, 194
  11. Simhadri, 2022, Results of the NeurIPS’21 challenge on billion-scale approximate nearest neighbor search, 176, 177
  12. Iris, Residual quantization with implicit neural codebooks, 20682
  13. Sun, SOAR: Improved quantization for approximate nearest neighbor search, 3189
  14. Thakur, BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models
  15. Izacard, 2023, Atlas: Few-shot learning with retrieval augmented language models, J. Mach. Learn. Res., 24, 1

Cited by

Sorted by citations

Items 901–1,000 of 1,008

Related

See all

Metadata

Authors
Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazaré, P.-E., Lomeli, M., Hosseini, L., & Jégou, H.
Affiliations
  • FAIR, Meta, Paris, France
  • Zilliz, Redwood City, CA, USA
  • DeepSeek (China) (CN)
  • Skip Labs, Paris, France
ORCID
Venue
IEEE Transactions on Big Data
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2026-04
Volume
12
Issue
2
Pages
346-361
ISSN
  • 2332-7790 (ISSN-L)
  • 2372-2096
DOI
10.1109/tbdata.2025.3618474
OpenAlex
W4415124086
Cited by
478
References
61
Citations by year
2026: 287
FWCI
167.83
Type
journal article
Language
en
Open access
Licence
Locations
IEEE Transactions on Big Data (publishedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Information Systems › Advanced Database Systems and Queries
Keywords
vector similarity search, vector databases, vector indexing, vector embeddings, vector clustering, vector compression, benchmarking

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