Non-Metric Space Library Manual

Bilegsaikhan Naidan, Leonid Boytsov, Yury Malkov, David Novak
8/22/2015
cs.MScs.IR

Official code: nmslib/nmslib (3,590 stars, Apache-2.0, last commit 2026-04-13).

Abstract

This document covers a library for fast similarity (k-NN)search. It describes only search methods and distances (spaces). Details about building, installing, Python bindings can be found online:https://github.com/searchivarius/nmslib/tree/v1.8/. Even though the library contains a variety of exact metric-space access methods, our main focus is on more generic and approximate search methods, in particular, on methods for non-metric spaces. NMSLIB is possibly the first library with a principled support for non-metric space searching.

View on arXivView PDF

Code Implementations(1)

nmslib/nmslibOfficial100%
Apache-2.0

Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

3,590462C, RJul 10, 20136 months agoApache-2.0
k-nn-graphsknn-searchneighborhood-graphsnon-metricvp-tree

Similar Papers

Billion-scale similarity search with GPUs

83% match1 repo41.2k2017

Clustered Hierarchical Entropy-Scaling Search of Astronomical and Biological Data

79% match2019

Large-Scale Data Parallelization of Product Quantization and Inverted Indexing Using Dask

79% match2026

LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search

77% match2023

GriSPy: A Python package for Fixed-Radius Nearest Neighbors Search

77% match1 repo412019

LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table

75% match1 repo132025

Cite this paper

@article{naidan2015nonmetric,
  title  = {Non-Metric Space Library Manual},
  author = {Bilegsaikhan Naidan and Leonid Boytsov and Yury Malkov and David Novak},
  year   = {2015},
  eprint = {1508.05470},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1508.05470}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1508.05470.svg)](https://codeofpaper.com/paper/1508.05470)

Discussion