2 nouveaux articles ! 2 new papers !

février, 21, 2010

Je suis très content d’annoncer aujourd’hui que deux articles ont été acceptés récemment. Je suis d’autant plus content qu’il s’agit dans les deux cas de travaux effectués en grande partie par des étudiants en thèse au sein de notre équipe. par ailleurs, l’article sur SpotRank annonce l’arrivée dans la « grande famille » des auteurs d’articles scientifiques de mon frère Guillaume, donc encore une bonne nouvelle.

Bref,voici les titres et abstracts :

SpotRank: A robust voting system for social news websites. Thomas Largillier, Guillaume Peyronnet and Sylvain Peyronnet. WICOW 2010.
abstract: We address the problem of designing a robust voting system for social news website. In a social news website people share content they found on the web, called news, then vote for those they like the most. Voting for a news is then considered as a recommendation, and news with a sufficient number of recommendations are displayed on a front page. Malicious users of such websites are entitled to boost their own content by manipulating the votes.
We present in this paper SpotRank, a robust algorithm that can demote the effect of manipulations, thus leading to a better quality of service for social news website users. We also present a website that implement this algorithm and show evidence of the efficiency of the approach, both from a statistical and human point of view.

Planning large data transfers in institutional grids. Fatiha Bouabache, Thomas Herault, Sylvain Peyronnet and Franck Cappello. Short paper at CCGRID 2010.
abstract:  In grid computing, many scientific and engineering applications require access to large amounts of distributed data. The size and number of these data collections has been growing rapidly in recent years and will continue to grow. The costs of data transmission take a significant part of the global execution time.
When communication streams flow concurrently on shared links, transport control protocols have issues allocating fair bandwidth to all the streams, and the network becomes sub- optimally used. One way to deal with this situation is to schedule the communications in a way that will induce an optimal use of the network.
This paper focuses on the case of large data transfers that can be completely described at the initialization time. In this case, a plan of data migration can be computed at initialization time, and then executed. However, this computation phase must take a small time when compared to the actual execution of the plan. We propose a best effort solution, to compute approximately, based on the uniform random sampling of possible schedules, a communication plan. We show the effectiveness of this approach both theoretically and by simulations.

Comments are closed.

Picture: courtesy of Abby Blank