26th European Conference on Artificial Intelligence (ECAI 2023)
Decentralized Federated Learning: Enabling Collaborative AI With Enhanced Trust and Efficiency
Conference tutorial on decentralized federated learning: foundations, architectures, security, privacy and practical experimentation, presented at ECAI 2023.
Abstract
This tutorial examines decentralized federated learning as an approach to collaborative artificial intelligence. It covers foundations, architectures, components, communication, security, privacy and optimization. Practical experimentation connects these concepts with the configuration and evaluation of federations, while application scenarios and open research challenges provide context for assessing trust and efficiency. The session took place at ECAI 2023 in Kraków, Poland, on 30 September 2023.
Authors
Keywords
Related publications
Publications connected by topic, method or application.
Journal of Healthcare Engineering
Breaching Subjects’ Thoughts Privacy: A Study with Visual Stimuli and Brain-Computer Interfaces
Mario Quiles Pérez, Enrique Tomás Martínez Beltrán, Sergio López Bernal, Alberto Huertas Celdrán, Gregorio Martínez Pérez
Brain-computer interfaces (BCIs) started being used in clinical scenarios, reaching nowadays new fields such as entertainment or learning. Using BCIs, neuronal activity can be monitored for various purposes, with the...
Information Fusion
Decentralized Federated Learning with Multimodal Prototypes for Heterogeneous Data
Enrique Tomás Martínez Beltrán, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Modalis addresses clients with different or missing modalities in decentralized learning. It exchanges compact class prototypes and aligns local representations to support collaboration across heterogeneous data.
Future Generation Computer Systems
FedEnD: Communication-efficient Federated Learning for non-IID data via decentralized ensemble distillation
Enrique Tomás Martínez Beltrán, Philip Giryes, Gérôme Bovet, Burkhard Stiller, Gregorio Martínez Pérez, Alberto Huertas Celdrán
FedEnD addresses heterogeneous client data and communication costs in federated learning. Clients train local specialists, exchange them once and distil a weighted ensemble using their own data without an auxiliary public dataset.
Related Research
Apr 2023 / Nov 2023
DEFENDIS: Decentralized Federated Learning for IoT Device Identification and Security
DEFENDIS develops a framework for uniquely identifying IoT devices in a distributed manner while solving security threats through decentralized federated learning.
Jan 2024 / Dec 2024
DATRIS: Decentralized AI for Trustworthy and Resource-efficient Intelligent Systems
Developed decentralized AI solutions addressing computational constraints and trust validation under armasuisse Cyber-Defence Campus sponsorship.
Jan 2024 / Jun 2026
ROBUST-6G: Smart, Automated and Reliable Security Service Platform for 6G
ROBUST-6G studies security mechanisms for 6G systems, including monitoring, secure data management, trustworthy AI services, federated learning, and threat response.