Venue - https://mdm-2026.github.io/venue.html#main
Full MDM Program - https://mdm-2026.github.io/program.html#main
8:30am onwards - Registration Open
9:00am - 10.30am - Workshop Opening Keynote
10.30am - 11:00am - Morning Tea
11:00am - 11.30am - TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning - Nan Zhang, Zishuo Wang, Shuyu Huang, Georgios Diamantopoulos, Nikos Tziritas, Panagiotis Oikonomou and Georgios Theodoropoulos
11:30am - 12.00pm - Integrating Heterogeneous Digital Twins in Federated Ecosystems - Christian Vergara Marcillo, Rami Bahsoon, Nikos Tziritas, Wendy Yanez-Pazmino, Panagiotis Oikonomou and Georgios Theodoropoulos
12:00pm - 12.30pm - IoT-Integrated Hybrid Machine Learning for Short- Term Raw Water Quality Forecasting - Dulashi Fernando, Samadhi Cooray, Praveen Jeyachandran, Dileesha Jayakodi, Prasanna Sumathipala and Salih Fousdeen
Ketnote Title - Distributed Machine Learning and Network Resource Allocation for Intelligent Edge Services
Speaker - Prof. Iordanis Koutsopoulos
Department of Informatics, Athens University of Economics and Business
Abstract: In this talk, we outline some research areas we work on for the last few years, on the foundations of intelligent trustworthy services at the resource-limited network edge. These questions require new synergies between Artificial Intelligence (AI) and Networking, and they fill the puzzle of ensuring trustworthy services in different sectors with autonomous vehicles, robotics, health, energy, agriculture, and more. Important milestones towards this goal are low-latency inference, personalization, explainability, continual model updates, energy efficiency, and low-latency communication with a network controller. Specifically, we will talk about: (1) running Large Language Models (LLMs) over a network of resource-constrained devices for low-latency inference; (2) developing new architectures for Split Federated Learning, by splitting and parallelizing the workload of training across devices; (3) achieving exact optimization in training personalized models with Federated Learning; (4) addressing both explainability and accuracy through a Multi-objective optimization framework; (5) introducing network awareness in Continual Learning; (6) using Multi-armed bandits to learn the optimal controller placement in Software-Defined Networks, and the optimal offloading policy for image processing tasks. We conclude with a prototype of a Digital Twin for a wireless network testbed and work on agentic AI, and we pave the way ahead.
Short Biography: Iordanis Koutsopoulos is Professor at the Department of Informatics of Athens University of Economics and Business (AUEB) since 2021. He obtained the Diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Athens, Greece in 1997, and the M.Sc. and Ph.D. degrees in Electrical and Computer Engineering from University of Maryland College Park (UMCP) in 1999 and 2002 respectively. He has been with AUEB since 2013. Prior to that (2005-2012), he has been with the Department of Electrical & Computer Engineering, University of Thessaly, Volos, Greece. During 2012, he was a visiting research scientist with Yahoo! Research Labs, Barcelona, Spain, and during 2005, he was a visiting scientist with the University of Washington, Seattle, USA. He has held other research positions in USA, at Hughes Network Systems, Hughes Research Labs, and Aperto Networks.