BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Monday Seminar : “WhatsUp : a P2P news items recommender
DTSTART:20110627T161500
DTSTAMP:20260427T225222Z
UID:c94c3bbc459dc975e428ed252314f2452a5a824ba90b2c051b080efd
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Anne-Marie Kermarrec - Senior Researcher at INRIA Rennes -
  IC Faculty candidate\nAbstract: The social face of the Web is now promine
 nt. Users have turned into active entities generating a huge volume of con
 tent. This leaves huge opportunities to build a new generation of user-cen
 tric (personalized) applications fully leveraging the social nature of the
  Web. Yet personalizing the Web requires to manage a lot of information at
  the users granularity which beyond the potential scalability issues makes
  such systems vulnerable to the "Big brother syndrom". In this talk I will
  introduce some design principles to build fully decentralized yet persona
 lized systems aimed for a large scale network with no central bottleneck s
 ingle point of failure or censorship authority. I will focus on WhatsUp a 
 p2p instant news system. WhatsUp’s collaborative filtering scheme levera
 ges the users opinions to dynamically maintain an implicit social network 
 and ensures that users subsequently receive news that are likely to match 
 their interests. Users with similar tastes are clustered using a similarit
 y metric reflecting long-standing and emerging (dis)interests. News items 
 are disseminated through a heterogeneous epidemic protocol that biases the
  choice of the targets towards those with similar interests and amplifies 
 the dissemination based on the interest of every actual news item. The pus
 h and asymmetric nature of the network created by WhatsUp provides a natur
 al support to limit privacy breaches. The evaluation of through large-scal
 e simulations a ModelNet emulation on a cluster and a PlanetLab deployment
  on real traces collected both from Digg as well as from a real news surve
 y will follow. Biography : Anne-Marie Kermarrec (http://www.irisa.fr/asap/
 akermarr) is a senior researcher at INRIA Rennes where she leads the distr
 ibuted systems group. She is the Principal Investigator of the ERC project
  Gossple and the chair of the ACM System software Award. She received the 
 Monpetit award from the French Academy of Science in 2011. Before joining 
 INRIA in February 2004 she was with Microsoft Research in Cambridge as a R
 esearcher since March 2000. Before that she obtained my Ph.D. from the Uni
 versity of Rennes (FRANCE) in October 1996. She also spent one year (1996-
 1997) at Vrije Universiteit in Amsterdam (The Netherlands) working with Ma
 arten van Steen and Andrew. S. Tanenbaum. Her research interetsts are in p
 eer to peer distributed systems epidemic algorithms social networks Web Sc
 ience. 
LOCATION:BC 01 https://plan.epfl.ch/?room==BC%2001
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR