A similarity cache can reply to a query for an object with similar objects stored locally. In some applications of similarity caches, queries and objects are naturally represented as points in a continuous space. Examples include 360° videos where user's head orientation - expressed in spherical coordinates - determines what part of the video needs to be retrieved, and recommendation systems where the objects are embedded in a finite-dimensional space with a distance metric to capture content dissimilarity. Existing similarity caching policies are simple modifications of classic policies like LRU, LFU, and qLRU and ignore the continuous nature of the space where objects are embedded. In this paper, we propose Grades, a new similarity caching policy that uses gradient descent to navigate the continuous space and find the optimal objects to store in the cache. We provide theoretical convergence guarantees and show Grades increases the similarity of the objects served by the cache in both applications mentioned above.

GRADES: Gradient descent for similarity caching / Sabnis, A.; Salem, T. S.; Neglia, G.; Garetto, M.; Leonardi, E.; Sitaraman, R. K.. - ELETTRONICO. - 2021:(2021), pp. 1-10. ((Intervento presentato al convegno 40th IEEE Conference on Computer Communications, INFOCOM 2021 tenutosi a Vancouver, BC, Canada nel 2021 [10.1109/INFOCOM42981.2021.9488757].

GRADES: Gradient descent for similarity caching

Leonardi E.;
2021

Abstract

A similarity cache can reply to a query for an object with similar objects stored locally. In some applications of similarity caches, queries and objects are naturally represented as points in a continuous space. Examples include 360° videos where user's head orientation - expressed in spherical coordinates - determines what part of the video needs to be retrieved, and recommendation systems where the objects are embedded in a finite-dimensional space with a distance metric to capture content dissimilarity. Existing similarity caching policies are simple modifications of classic policies like LRU, LFU, and qLRU and ignore the continuous nature of the space where objects are embedded. In this paper, we propose Grades, a new similarity caching policy that uses gradient descent to navigate the continuous space and find the optimal objects to store in the cache. We provide theoretical convergence guarantees and show Grades increases the similarity of the objects served by the cache in both applications mentioned above.
978-1-6654-0325-2
File in questo prodotto:
File Dimensione Formato  
sabnis21infocom.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 2.48 MB
Formato Adobe PDF
2.48 MB Adobe PDF Visualizza/Apri
GRADES_Gradient_Descent_for_Similarity_Caching.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 5.94 MB
Formato Adobe PDF
5.94 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11583/2921432