Week 01 | Introduction to Federated Learning | Theory and Applications of Federated Learning

Theory and Applications of Federated Learning Week 01 — Introduction to Federated Learning This lecture introduces the fundamental concepts, motivation, and basic architecture of Federated Learning (FL). In this session, we discuss why federated learning is needed, how it differs from centralized and conventional distributed learning, and how a basic federated training process operates. Topics covered: • Motivation for Federated Learning • Data privacy, ownership, and decentralized data generation • Centralized vs. local-only vs. distributed vs. federated learning • Basic federated learning workflow • Clients, server, local training, aggregation, and communication rounds • Cross-device vs. cross-silo federated learning • Major application domains • Current research challenges and open problems Course: Theory and Applications of Federated Learning Level: Graduate Language: English Course Materials / GitHub: https://github.com/faranaksadatsolat/... Instructor: Faranak Solat Department of AI & Data Science, Sejong University Main References: H. Ludwig and N. Baracaldo (Eds.), Federated Learning: A Comprehensive Overview of Methods and Applications, Springer, 2022. P. Kairouz et al., “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, 2021. This lecture is intended for educational purposes as part of a graduate-level course on federated learning. #FederatedLearning #MachineLearning #ArtificialIntelligence #DistributedLearning #PrivacyPreservingAI #EdgeAI #GraduateCourse