10000 GitHub - dongdeng/QALSH
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

dongdeng/QALSH

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

QALSH: Query-Aware Locality-Sensitive Hashing

Version: 1.4.0

Release date: 03-10-2017

Last Modified: 25-04-2018

Introduction

This package is written in the C++ programming language. It contains two external LSH schemes QALSH and QALSH+ for high-dimensional c-Approximate Nearest Neighbor (or simply c-ANN) search under l_p norm, where p \in (0, 2].

Usage

We provide a Makefile and a shell script (i.e., run_mnist.sh) as a running example for comipling and running the package. Before running this package, please ensure the input format of the dataset and query set is correct. We give a sample dataset and query set (i.e., Mnist) for your reference.

We also share the shell scripts (i.e., run_sift.sh, run_gist.sh, run_trevi.sh, and run_p53.sh) for the users who would like to reproduce the results presented in PVLDB 2015 and VLDBJ 2017. The datasets Sift, Gist, Trevi, and P53 we used can be downloaded from the following links:

Authors

Relevant Papers

The papers for the package of QALSH have been published in PVLDB 2015 and VLDBJ 2017, which are displayed as follows:

  • Qiang Huang, Jianlin Feng, Yikai Zhang, Qiong Fang, and Wilfred Ng. Query-Aware Locality-Sensitive Hashing for Approximate Nearest Neighbor Search. In Proceedings of the VLDB Endowment (PVLDB), 9(1): 1 - 12, 2015.

  • Qiang Huang, Jianlin Feng, Qiong Fang, Wilfred Ng, and Wei Wang. Query-Aware Locality-Sensitive Hashing Scheme for l_p Norm. The VLDB Journal, 26(5): 683 – 708, 2017.

If you use the package for publications, please cite the papers above. Thank you.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 85.5%
  • q 6.1%
  • C 4.4%
  • Shell 3.8%
  • Makefile 0.2%
0