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 accessAbstract
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.
Integrity signals
Registry
Cites
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.
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
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 2×
“Datasets: Early datasets are based on keypoint features like SIFT [39] used in image matching.”
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638
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
Self-citationLocality-sensitive hashing scheme based on p-stable distributions
Datar, M., Immorlica, N., Indyk, P., & Mirrokni, V. (2004) · Annual Symposium on Computational Geometry (SoCG) · doi:10.1145/997817.997857 · Cited by 2,971
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 8×
“Given this search algorithm, relying on a pure k-nearest neighbor graph is not optimal because neighbors are redundant.”
InfluentialSelf-citationDeep Clustering for Unsupervised Learning of Visual Features
Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_9 · Cited by 2,674
Self-citation
Flagged first, then by citations
Research works printed but not linked: 15
- Paterek, Improving regularized singular value decomposition for collaborative filtering, 5
- Radford, Learning transferable visual models from natural language supervision, 8748
- 10.5555/3524938.3525087 · DOI
- Matsui, 2018, A survey of product quantization, ITE Trans. Media Technol. Appl., 16, 2
- Guo, Accelerating large-scale inference with anisotropic vector quantization, 3887
- Subramanya, DiskANN: Fast accurate billion-point nearest neighbor search on a single node, 13766
- Simhadri, 2022, Results of the NeurIPS’21 challenge on billion-scale approximate nearest neighbor search, 176, 177
- Babenko, Efficient indexing of billion-scale datasets of deep descriptors, 2055
- Morozov, Non-metric similarity graphs for maximum inner product search, 4726
- Weber, 1998, A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces, VLDB, 98, 194
- Simhadri, 2022, Results of the NeurIPS’21 challenge on billion-scale approximate nearest neighbor search, 176, 177
- Iris, Residual quantization with implicit neural codebooks, 20682
- Sun, SOAR: Improved quantization for approximate nearest neighbor search, 3189
- Thakur, BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models
- Izacard, 2023, Atlas: Few-shot learning with retrieval augmented language models, J. Mach. Learn. Res., 24, 1
Cited by
Sorted by citations
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267
The power of noise: Redefining retrieval for rag systems
Cuconasu, F., Trappolini, G., Siciliano, F., Filice, S., Campagnano, C., Maarek, Y., Tonellotto, N., & Silvestri, F. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3657834 · Cited by 236
Evaluating Retrieval Quality in Retrieval-Augmented Generation
Salemi, A., & Zamani, H. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657957 · Cited by 259
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
Zhao, X., Liu, S., Yang, S.-Y., & Miao, C. (2025) · Proceedings of the ACM on Web Conference 2025 · doi:10.1145/3696410.3714782 · Cited by 116
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
- Venue
- IEEE Transactions on Big Data
- Published
- 2026-04
- Volume
- 12
- Issue
- 2
- Pages
- 346-361
- ISSN
- 2332-7790 (ISSN-L)
- 2372-2096
- OpenAlex
- W4415124086
- Cited by
- 478
- References
- 61
- Citations by year
- 2026: 287
- FWCI
- 167.83
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- 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
