Papers › LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

24 Oct 2024arXiv:2410.18926archive 2025-07-28

Elias Jääsaari, Ville Hyvönen, Teemu Roos

Approximate nearest neighbor (ANN) search is a key component in many modern machine learning pipelines; recent use cases include retrieval-augmented generation (RAG) and vector databases. Clustering-based ANN algorithms, that use score computation methods based on product quantization (PQ), are often used in industrial-scale applications due to their scalability and suitability for distributed and disk-based implementations. However, they have slower query times than the leading graph-based ANN algorithms. In this work, we propose a new supervised score computation method based on the observation that inner product approximation is a multivariate (multi-output) regression problem that can be solved efficiently by reduced-rank regression. Our experiments show that on modern high-dimensional data sets, the proposed reduced-rank regression (RRR) method is superior to PQ in both query latency and memory usage. We also introduce LoRANN, a clustering-based ANN library that leverages the proposed score computation method. LoRANN is competitive with the leading graph-based algorithms and outperforms the state-of-the-art GPU ANN methods on high-dimensional data sets.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.18926")

Code

Syntology Ran 0 of 20 code samples harvested from 2 repositories linked to this paper; 20 have no recorded run.

By repository: official repository: 20 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ejaasaari/lorann officialmentioned on GitHubjaxMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested; 0 ran; 0 honoured the contract we drafted; 20 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

20unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

algorithm_status ejaasaari/lorann-experiments/ann_benchmarks/definitions.py official repository unverified MIT (permissive) · 1a459680e482b1e0 · report
build ejaasaari/lorann-experiments/install.py official repository unverified MIT (permissive) · 1a2ffd7252fad4b2 · report
build_multiprocess ejaasaari/lorann-experiments/install.py official repository unverified MIT (permissive) · eb502608c05c9c3a · report
compute_V ejaasaari/lorann/python/lorann_gpu/lorann_gpu.py official repository unverified MIT (permissive) · ba29d4db272d5078 · report
compute_distance ejaasaari/lorann-experiments/ann_benchmarks/distance.py official repository unverified MIT (permissive) · 33781da3207cc49d · report
compute_recall ejaasaari/lorann/python/lorann/lorann.py official repository unverified MIT (permissive) · 67137b50ff87ea9b · report
config_write ejaasaari/lorann-experiments/convert_algos.py official repository unverified MIT (permissive) · 71f7ee0bb635fb1a · report
convert_color ejaasaari/lorann-experiments/create_website.py official repository unverified MIT (permissive) · 24ec4bb9c63da4f6 · report
convert_linestyle ejaasaari/lorann-experiments/create_website.py official repository unverified MIT (permissive) · feb0a5830b75c0f5 · report
euclidean ejaasaari/lorann-experiments/ann_benchmarks/distance.py official repository unverified MIT (permissive) · 58e6e4420d6b0cef · report
float_parse_entry ejaasaari/lorann-experiments/ann_benchmarks/data.py official repository unverified MIT (permissive) · 44fa38f4dba6c740 · report
float_unparse_entry ejaasaari/lorann-experiments/ann_benchmarks/data.py official repository unverified MIT (permissive) · 43546c638e833781 · report
get_config_files ejaasaari/lorann-experiments/ann_benchmarks/definitions.py official repository unverified MIT (permissive) · 781712699c80561e · report
get_dataset ejaasaari/lorann-experiments/ann_benchmarks/datasets.py official repository unverified MIT (permissive) · 1832a37264ff8488 · report
get_dataset_fn ejaasaari/lorann-experiments/ann_benchmarks/datasets.py official repository unverified MIT (permissive) · 08c7a13d549d2592 · report
get_run_desc ejaasaari/lorann-experiments/create_website.py official repository unverified MIT (permissive) · 239f62264b6ae120 · report
int_parse_entry ejaasaari/lorann-experiments/ann_benchmarks/data.py official repository unverified MIT (permissive) · 378ed3f6e88f78c2 · report
jaccard ejaasaari/lorann-experiments/ann_benchmarks/distance.py official repository unverified MIT (permissive) · df5a5ca06135cc3f · report
replace_hyphens_in_keys ejaasaari/lorann-experiments/convert_algos.py official repository unverified MIT (permissive) · a78b6c11cea19a3d · report
train_test_split ejaasaari/lorann-experiments/ann_benchmarks/datasets.py official repository unverified MIT (permissive) · 762ddcae80faee0b · report

Tasks

ClusteringQuantizationRAGRetrieval-augmented Generationregression

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections