BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.28348.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260404T101808Z
CREATED:20240703T125955Z
DESCRIPTION:Abstract: In this talk we discuss approaches for distributed ma
 chine learning (ML) in resource-constrained edge-supported Internet of Thi
 ngs (IoT) networks. Federated Learning (FL) and Split Learning (SL) are po
 pular approaches in such wireless edge networks. First\, we present Early 
 Exit of Communication (EEoC)\, which adaptively splits ML inference in an 
 IoT edge computing environment to meet latency and energy constraints. Thi
 s layer-based (vertically partitioned) approach has been extended by Distr
 ibuted Micro-Split Deep Learning in Heterogeneous Dynamic IoT (DISNET)\, w
 hich adds horizontal partitioning to better support flexible\, distributed
 \, and parallel execution of neural network models on heterogeneous IoT de
 vices under dynamic conditions. Then\, we also consider the training aspec
 t by developing and evaluating Adaptive REsource-aware Split-learning (ARE
 S)\, a scheme for efficient model training in IoT systems. Recent work sug
 gests Dynamic FL (DFL) for heterogeneous IoT\, which uses resource-aware S
 L and FL based on similarity-based layer-wise model aggregation.Bio: Prof.
  Dr. Torsten Braun is head of the Communication and Distributed Systems (C
 DS) research group at the Institute of Computer Science\, University of Be
 rn\, where he has been a full professor since 1998. He got the Ph.D. degre
 e from University of Karlsruhe (Germany) in 1993. From 1994 to 1995\, he w
 as a guest scientist at INRIA Sophia-Antipolis (France). From 1995 to 1997
 \, he worked at the IBM European Networking Centre Heidelberg (Germany) as
  a project leader and senior consultant. He has been a vice president of t
 he SWITCH (Swiss Research and Education Network Provider) Foundation from 
 2011 to 2019. He has been a Director of the Institute of Computer Science 
 and Applied Mathematics at University of Bern between 2007 and 2011\, and 
 from 2019 to 2021.
DTSTART;TZID=Europe/Paris:20240710T100000
DTEND;TZID=Europe/Paris:20240710T100000
LAST-MODIFIED:20240703T131003Z
LOCATION:Aula Magna DIAG
SUMMARY:Federated and Split Machine Learning in the Internet of Things - Pr
 of. Dr. Torsten Braun
URL;TYPE=URI:https://www.diag.uniroma1.it/node/28348
END:VEVENT
END:VCALENDAR