Fast Adaptive Approximate Nearest Neighbor Search with Cluster-Shaped Indices

In this study, we propose a novel adaptive algorithm for approximate nearest neighbor (ANN) search, based on the inverted file (IVF) index (cluster-based index) and online query complexity classification. The concept of the classical IVF search implemented in vector databases is as follows: all data...

Descripció completa

Dades bibliogràfiques

Autors principals:	Vladimir Kazakovtsev, Mikhail Plekhanov, Alexandr Naumchev, Guzel Shkaberina, Igor Masich, Lyudmila Egorova, Alena Stupina, Aleksey Popov, Lev Kazakovtsev
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2025-10-01
Col·lecció:	Big Data and Cognitive Computing
Matèries:	approximate nearest neighbors inverted file index vector databases adaptive search
Accés en línia:	https://www.mdpi.com/2504-2289/9/10/254
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!