Εφαρµογές Συνεχούς και Οµοσπονδιακής Συνεργατικής Μάθησης

Abstract

In the modern digital era, the exponential growth of data generated at the network edge driven by thousands of Internet of Things (IoT) devices, has unlocked unprecedented opportunities for Artificial Intelligence (AI) and Machine Learning (ML). However the utilization of this decentralized data is increasingly constrained by strict privacy regulations (e.g., GDPR, HIPAA) and bandwidth limitations, rendering traditional centralized training approaches often prohibitive. Federated Learning (FL) has emerged as a transformative solution to these challenges that enables collaborative model training while preserving data privacy.