GRADES: Gradient Descent for Similarity Caching
| Autor: | Anirudh Sabnis, Emilio Leonardi, Ramesh Sitaraman, Tareq SI SALEM, Michele Garetto, Giovanni Neglia |
|---|---|
| Přispěvatelé: | University of Massachusetts [Amherst] (UMass Amherst), University of Massachusetts System (UMASS), Université Côte d'Azur (UCA), Network Engineering and Operations (NEO ), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Università degli studi di Torino (UNITO), Politecnico di Torino - Dipartimento di Elettronica (Politecnico di Torino) (CERCOM), Università degli studi di Torino = University of Turin (UNITO), Politecnico di Torino = Polytechnic of Turin (Polito) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Theoretical computer science
Computer Networks and Communications Computer science Space (commercial competition) Recommender system Caching Videos Similarity (network science) Simple (abstract algebra) Convergence (routing) Machine learning Navigation Conferences Machine learning Extraterrestrial measurements Steady-state Videos Convergence [INFO]Computer Science [cs] Electrical and Electronic Engineering Hardware_MEMORYSTRUCTURES Conferences stochastic gradient Object (computer science) Navigation Computer Science Applications Steady-state Cache Extraterrestrial measurements Gradient descent Convergence Software |
| Zdroj: | IEEE International Conference on Computer Communications (INFOCOM 2021) IEEE International Conference on Computer Communications (INFOCOM 2021), May 2021, Virtual Conference, United States IEEE INFOCOM 2021-IEEE Conference on Computer Communication INFOCOM IEEE/ACM Transactions on Networking IEEE/ACM Transactions on Networking, 2022, pp.1-12. ⟨10.1109/TNET.2022.3187044⟩ INFOCOM 2021-IEEE International Conference on Computer Communications INFOCOM 2021-IEEE International Conference on Computer Communications, May 2021, Virtual Conference, United States. ⟨10.1109/INFOCOM42981.2021.9488757⟩ |
| ISSN: | 1063-6692 |
| DOI: | 10.1109/TNET.2022.3187044⟩ |
| Popis: | International audience; 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. This is for example the case of 360 • videos where user's head orientation-expressed in spherical coordinates-determines what part of the video needs to be retrieved, or of recommendation systems where a metric learning technique is used to embed the objects in a finite dimensional space with an opportune distance 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 appropriate 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|