CoChat

Cache locality is not enough: high-performance nearest neighbor search with product quantization fast scan

André, Fabien, Kermarrec, Anne-Marie, Le Scouarnec, Nicolas · 2015 · Proceedings of the VLDB Endowment
Cited by 70

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

Nearest Neighbor (NN) search in high dimension is an important feature in many applications (e.g., image retrieval, multimedia databases). Product Quantization (PQ) is a widely used solution which offers high performance, i.e., low response time while preserving a high accuracy. PQ represents high-dimensional vectors (e.g., image descriptors) by compact codes. Hence, very large databases can be stored in memory, allowing NN queries without resorting to slow I/O operations. PQ computes distances to neighbors using cache-resident lookup tables, thus its performance remains limited by (i) the many cache accesses that the algorithm requires, and (ii) its inability to leverage SIMD instructions available on modern CPUs. In this paper, we advocate that cache locality is not sufficient for efficiency. To address these limitations, we design a novel algorithm, PQ Fast Scan, that transforms the cache-resident lookup tables into small tables, sized to fit SIMD registers. This transformation allows (i) in-register lookups in place of cache accesses and (ii) an efficient SIMD implementation. PQ Fast Scan has the exact same accuracy as PQ, while having 4 to 6 times lower response time (e.g., for 25 million vectors, scan time is reduced from 74ms to 13ms).

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 · 10.14778/2856318.2856324

Cites

3 of 3 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

  • Least squares quantization in PCM

    Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836 · cited 1×

    “…d → C = ( c 0 , . . . , c k − 1 ) We consider Lloyd-optimal quantizers which map vectors to their closest centroids and can be built using k-means [20]. q( x ) = arg min Vector quantizers allow representing vectors by compact codes by using the index i of their closest centroid c i as…”
  • 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 9×

    “We focus on product quantizers with 2 centroids as they offer a good tradeoff between complexity and quality for NN search [14].”
    BackgroundMethodInfluential
  • Experiencing SAX: A novel symbolic representation of time series

    Lin, J., Keogh, E., Wei, L., & Lonardi, S. (2007) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-007-0064-z · Cited by 1,618 · cited 1×

    “Compression schemes, either generic [23, 12, 3, 25] or specific (e.g., SAX for time series [18]), have been widely adopted in database systems.”

Cited by

See all 70

Metadata

Authors
André, F., Kermarrec, A.-M., & Le Scouarnec, N.
Venue
Proceedings of the VLDB Endowment
Published
2015-12
Volume
9
Issue
4
Pages
288-299
ISSN
2150-8097 (ISSN-L)
OpenAlex
W2204555070
Cited by
70
References
3
FWCI
2.89
Type
journal article
Language
en
Open access
closed

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.