Anne-Marie Kermarrec is a research director at Inria where she leads the ASAP (as Scalable As Possible) research group on large-scale dynamic distributed systems. Before that she has been with Vrije Universteit and  Microsoft Research Cambridge. She was the PI  of an ERC Strating Grant (2008-2013) and an ERC Proof of Concept Grant (2013). 

AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI   Info

Expert Audience

English

90 Minutes

Saarbrücken

The ever-growing amount of data available on the Internet clearly calls for personalization. Yet, the most effective personalization schemes, such as those based on collaborative filtering (CF), are notoriously resource greedy. We argue that scalable infrastructures relying on  P2P design can scale to that increasing number of users, data and dynamics. We will present a novel scalable k-nearest neighbor protocol, which P2P flavor provides scalability by design. This protocol provides each user with an implicit social network composed of users with similar tastes in a given application. This protocol has been instanciated in various infrastructures on several applications (recommendation, top-k, serach, etc.) (1) A P2P system, WhatsUp, a collaborative filtering system for disseminating news items in a large-scale dynamic setting with no central authority; (2) A hybrid recommendation infrastructure HyRec, an online cost-effective scalable system for CF personalization, offloading CPU-intensive recommendation tasks to front-end client browsers, while retaining storage and orchestration tasks within back-end servers; (3) A cloud-based centralized  engine providing real time recommendations.

Claudia Richter

9303 9103

--email hidden

Yes

Kaiserslautern

G26

111

passcode not visible

logged in users only