BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.3.6//EN
BEGIN:VEVENT
UID:955@lincs.fr
DTSTART;TZID=Europe/Paris:20260907T140000
DTEND;TZID=Europe/Paris:20260907T170000
DTSTAMP:20260903T135245Z
URL:https://www.lincs.fr/events/peer-to-peer-protocols-for-efficient-and-r
 esilient-decentralized-learning-theory-design-and-evaluation/
SUMMARY:Peer-to-Peer Protocols for Efficient and Resilient Decentralized
 Learning: Theory\, Design and Evaluation
DESCRIPTION:Jury composition:\n- Prof. Maria POTOP-BUTUCARU\, Sorbonne
 Université (PhD advisor)\n- Prof. Sébastien TIXEUIL\, Sorbonne
 Université (PhD co-advisor)\n- Dr. Davide FREY\, Inria (Reviewer)\n- Prof.
 Mohamed MOSBAH\, Institut Polytechnique de Bordeaux / LaBRI  (Reviewer)\n-
 Prof. Luciana ARANTES\, Sorbonne Université (Examiner)\n- Prof. Pascal
 FELBER\, University of Neuchâtel (Examiner)\n- Prof. François TAIANI\,
 Université de Rennes / Inria (Examiner)\n- Prof. Véronique VEQUE\,
 Université Paris-Saclay (Examiner)\n\nAbstract:\nWhile artificial
 intelligence largely relies on centralized infrastructures\, growing
 concerns about data privacy\, digital sovereignty\, resilience\, and
 scalability call for rethinking collaboration among distributed entities.
 Peer-to-peer architectures offer attractive robustness properties and avoid
 single\npoints of failure\, yet harnessing them efficiently for federated
 learning remains a major challenge.\nThis thesis addresses this problem
 through a layered architecture that bridges networking and decentralized
 learning. Its contributions unfold into four protocols. The peer-sampling
 protocols Elevator and Lift let a structured multi-hub topology emerge in a
 fully decentralized manner — a self-organized hub election for Elevator\,
 made robust against Byzantine behaviour by Lift. HEAL then exploits this
 hierarchical structure to deliver decentralized learning whose convergence
 speed rivals federated learning while remaining resilient to crashes and
 churn. Finally\, FLAIR adapts these principles to wireless sensor networks
 through a resource-aware election of cluster heads. This work\ncombines
 experimentation and theoretical analysis. The proposed protocols are
 evaluated at large scale through simulation (PeerSim\, ns-3) and\, for
 Elevator\, through a real implementation over TCP/IP\; in addition\, a
 formal analysis establishes the convergence of Elevator toward its
 multi-hub topology.
CATEGORIES:PhD Defense
LOCATION:LIP 6 - Tour 24/25\, 4 place Jussieu\, Paris\, 75005\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=4 place Jussieu\, Paris\,
 75005\, France;X-APPLE-RADIUS=100;X-TITLE=LIP 6 - Tour 24/25:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR