ECSA 2025
Mon 15 - Fri 19 September 2025 Limassol, Cyprus

The emerging Federated Learning (FL) paradigm offers significant advantages over the traditional centralized architecture of machine learning (ML) systems by reducing privacy risks and distributing computational load. However, the network topology (i.e., the number of available clients, and their characteristics) has a critical impact on performance metrics. This work investigates how application-specific requirements can drive architectural choices and how such choices impact FL performance. Specifically, we present a requirement-driven reference architecture for FL applications. Using a standard benchmark, we empirically evaluate 20 architecture realizations in different boundary conditions. The effectiveness of each realization is assessed based on the accuracy of the trained model and the wall-clock time required to complete the training. By combining our experimental results with existing qualitative studies from the literature, we devise a guideline to help prospective users select the most suitable configuration based on their application-specific non-functional requirements.

Wed 17 Sep

Displayed time zone: Athens change

16:00 - 17:45
Session 3 - Self-Adaptive, Secure and Federated Learning SystemsResearch Papers / Journal First at Phoenix
Chair(s): Dalila Tamzalit Nantes Université
16:00
30m
Full-paper
Model-based Proactive Self-Adaptation for Cloud SystemsResearch Track Paper
Research Papers
Raphael Straub Ulm University, Sarah Sophie Stieß University of Stuttgart, Germany, Steffen Becker University of Stuttgart, Matthias Tichy Ulm University
16:30
30m
Full-paper
SAFER-D: A Self-Adaptive Security Framework for Distributed Computing ArchitecturesResearch Track Paper
Research Papers
Marco Stadler Johannes Kepler University Linz, Michael Vierhauser University of Innsbruck, Michael Riegler Johannes Kepler University Linz, Daniel Waghubinger Johannes Kepler University Linz, Johannes Sametinger Johannes Kepler University Linz
Link to publication DOI Pre-print File Attached
17:00
30m
Full-paper
Architecting Federated Learning Systems: A Requirement-Driven ApproachResearch Track Paper
Research Papers
Luciano Baresi Politecnico di Milano, Livia Lestingi DEIB, Politecnico di Milano, Iyad Wehbe Politecnico di Milano
17:30
15m
Short-paper
Smart Ecosystems and Digital Twins: An Architectural Perspective and a FIWARE-Based SolutionJournal First Paper
Journal First
Franca Rocco di Torrepadula University of Naples Federico II, Alessandra Somma University of Naples Federico II, Alessandra De Benedictis University of Naples Federico II, Nicola Mazzocca University of Naples Federico II