HyRec: Leveraging Browsers for Scalable Recommenders

Abstract : The ever-growing amount of data available on the Internet calls for personalization. Yet, the most effective personalization schemes, such as those based on collaborative filtering (CF), are notoriously resource greedy. This paper presents HyRec, an online cost-effective scalable system for user-based CF personalization. HyRec offloads recommendation tasks onto the web browsers of users, while a server orchestrates the process and manages the relationships be-tween user profiles. HyRec has been fully implemented and extensively evaluated on several workloads from MovieLens and Digg. We convey the abil-ity of HyRec to reduce the operation costs of content providers by nearly 50% and to provide a 100-fold improvement in scala-bility with respect to a centralized (or cloud-based recommender approach), while preserving the quality of personalization. We also show that HyRec is virtually transparent to users and induces only 3% of the bandwidth consumption of a P2P solution.
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download

https://hal.inria.fr/hal-01080016
Contributor : Davide Frey <>
Submitted on : Tuesday, November 4, 2014 - 1:53:20 PM
Last modification on : Friday, November 16, 2018 - 1:39:17 AM
Long-term archiving on : Thursday, February 5, 2015 - 10:35:37 AM

File

main (2).pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

Citation

Antoine Boutet, Davide Frey, Rachid Guerraoui, Anne-Marie Kermarrec, Rhicheek Patra. HyRec: Leveraging Browsers for Scalable Recommenders. Middleware 2014, Dec 2014, Bordeaux, France. ⟨10.1145/2663165.2663315⟩. ⟨hal-01080016⟩

Share

Metrics

Record views

2768

Files downloads

801