Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH

In this paper we propose the creation of generic LSH families for the angular distance based on Johnson-Lindenstrauss projections. We show that feature hashing is a valid J-L projection and propose two new LSH families based on feature hashing. These new LSH families are tested on both synthetic an...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Argerich, Luis, Golmar, Natalia
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2017
Materias:
Ciencias Informáticas
Locality Sensitive Hashing
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/63169
http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/AGRANDA/AGRANDA-01.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-63169
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Locality Sensitive Hashing
spellingShingle Ciencias Informáticas
Locality Sensitive Hashing
Argerich, Luis
Golmar, Natalia
Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
topic_facet Ciencias Informáticas
Locality Sensitive Hashing
description In this paper we propose the creation of generic LSH families for the angular distance based on Johnson-Lindenstrauss projections. We show that feature hashing is a valid J-L projection and propose two new LSH families based on feature hashing. These new LSH families are tested on both synthetic and real datasets with very good results and a considerable performance improvement over other LSH families. While the theoretical analysis is done for the angular distance, these families can also be used in practice for the euclidean distance with excellent results [2]. Our tests using real datasets show that the proposed LSH functions work well for the euclidean distance.
format Objeto de conferencia
Objeto de conferencia
author Argerich, Luis
Golmar, Natalia
author_facet Argerich, Luis
Golmar, Natalia
author_sort Argerich, Luis
title Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
title_short Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
title_full Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
title_fullStr Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
title_full_unstemmed Generic LSH Families for the Angular Distance Based on Johnson-Lindenstrauss Projections and Feature Hashing LSH
title_sort generic lsh families for the angular distance based on johnson-lindenstrauss projections and feature hashing lsh
publishDate 2017
url http://sedici.unlp.edu.ar/handle/10915/63169
http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/AGRANDA/AGRANDA-01.pdf
work_keys_str_mv AT argerichluis genericlshfamiliesfortheangulardistancebasedonjohnsonlindenstraussprojectionsandfeaturehashinglsh
AT golmarnatalia genericlshfamiliesfortheangulardistancebasedonjohnsonlindenstraussprojectionsandfeaturehashinglsh
bdutipo_str Repositorios
_version_ 1764820480535035905

Ejemplares similares