Section: Partnerships and Cooperations
European initiatives
FP7 projects
ALLYOURS ERC Proof of Concept
-
Title: AllYours: A distributed privacy-aware instant item recommender
-
See also: http://www.gossple.fr
-
Abstract: The goal of this PoC proposal is to boost the creation of a start-up (AllYours/MediEgo ) targeting both Internet users as well as small to medium companies (SME) offering full-fledged personalization in notification systems. AllYours is a direct outcome from the Gossple ERC Starting Grant, and more specifically from one of the activities conducted within the project, that today involves most of the team and forces. In the Gossple ERC SG project, we have invented the concept of implicit social network, built and maintained in a fully decentralized manner so that each user is in charge of her own personalized data, addressing both the privacy concern that users may have with respect to Big Brother-like companies, and scalability as the resources present at the edges of the Internet can then be fully leveraged. The Gossple social network has been the basis of several Web 2.0 applications in order to personalize Web functionalities within the project, such as search, recommendation, query expansion, top-k queries, etc. More specifically, we have been applying the Gossple social network to personalized notification, defining on top of it a novel dissemination protocol. This is P2P-AllYours currently under development. Our MediEgo software is now applied to centralized systems for recommendations.
TOWARD THE ALLYOURS START-UP
-
Title: TOWARD THE ALLYOURS START-UP: Focus on the mobile version
-
See also: http://www.gossple.fr
-
Abstract: The goal of the Activity proposal is to turn the inventions from the ERC Starting Grant Project Gossple to innovation by setting up a start-up (AllYours) targeting both Internet users as well as small to medium companies (SME) offering full-fledged personalization in notification systems. This proposal focuses on the mobile versions of AllYours software. While the wired setting is a goal of the foreseen startup, this proposal will focus on the mobile versions of E-AllYours and P2P AllYours that will be experimented on the live platform provided by the TrentoRise partners.
ERC SG Gossple
-
See also: http://www.gossple.fr
-
Abstract: Anne-Marie Kermarrec is the principal investigator of the Gossple ERC starting Grant (Sept. 2008 - Sept. 2013). Gossple aims at providing a radically new approach to navigating the digital information universe. This project has been granted a 1.250.000 euros budget for 5 years.
Gossple aims at radically changing the navigation on the Internet by placing users affinities and preferences at the heart of the search process. Complementing traditional search engines, Gossple will turn search requests into live data to seek the information where it ultimately is: at the user. Gossple precisely aims at providing a fully decentralized system, self-organizing, able to discover, capture and leverage the affinities between users and data.
Collaborations in European programs, except FP7
Transform Marie Curie Initial Training Network (ITN)
Participants : Tyler Crain, Eleni Kanellou, Anne-Marie Kermarrec, Michel Raynal.
-
Project title: Theoretical Foundations of Transactional Memory
-
Other partners: Foundation for Research and Technology Hellas ICS FORTH Greece, University of Rennes I UR1 France, Ecole Polytechnique Federale de Lausanne EPFL Switzerland, Technische Universitaet Berlin TUB Germany, and Israel Institute of Technology Technion.
-
Abstract: Transform is a Marie Curie Initial Training Networks European project devoted to the Theoretical Foundations of Transactional Memory ( Major chip manufacturers have shifted their focus from trying to speed up individual processors into putting several processors on the same chip. They are now talking about potentially doubling efficiency on a 2x core, quadrupling on a 4x core and so forth. Yet multi-core is useless without concurrent programming. The constructors are now calling for a new software revolution: the concurrency revolution. This might look at first glance surprising for concurrency is almost as old as computing and tons of concurrent programming models and languages were invented. In fact, what the revolution is about is way more than concurrency alone: it is about concurrency for the masses. The current parallel programming approach of employing locks is widely considered to be too difficult for any but a few experts. Therefore, a new paradigm of concurrent programming is needed to take advantage of the new regime of multicore computers. Transactional Memory (TM) is a new programming paradigm which is considered by most researchers as the future of parallel programming. Not surprisingly, a lot of work is being devoted to the implementation of TM systems, in hardware or solely in software. What might be surprising is the little effort devoted so far to devising a sound theoretical framework to reason about the TM abstraction. To understand properly TM systems, as well as be able to assess them and improve them, a rigorous theoretical study of the approach, its challenges and its benefits is badly needed. This is the challenging research goal undertaken by this MC-ITN. Our goal through this project is to gather leading researchers in the field of concurrent computing over Europe, and combine our efforts in order to define what might become the modern theory of concurrent computing. We aim at training a set of Early Stage Researchers (ESRs) in this direction and hope that, in turn, these ESRs will help Europe become a leader in concurrent computing. Its keywords are Transactional Memory, Parallelization Mechanisms, Parallel Programming Abstractions, Theory, Algorithms, Technological Sciences