PART I: Fundamentals and Key Challenges 1. Gradient Descent-Type Methods: Background and Simple Unified Convergence Analysis 2. Considerations on the Theory of Training Models with Differential Privacy 3. Personalized Federated Learning: Theory and Practice 4. Privacy Preserving Federated Learning: Algorithms and Guarantees 5. Securing Federated Learning: Defending Against Poisoning and Evasion Attacks 6. Adversarial Robustness in Federated Learning 7. Evaluating Gradient Inversion Attacks and Defenses
PART II: Emerging Topics 8. Fairness in Federated Learning 9. Meta Federated Learning 10. Topology-Aware Federated Learning 11. Multi-Tier Federated Learning with Vertically and Horizontally Partitioned Data 12. Vertical Asynchronous Federated Learning 13. Hyperparameter Tuning for Federated Learning - Systems and Practices 14. Hyper-parameter Optimization for Federated Learning 15. Federated Sequential Decision-Making: Bayesian Optimization, Reinforcement Learning and Beyond 16. Data Valuation in Federated Learning
PART III: Applications 17. Incentives in Federated Learning 18. Introduction to Federated Quantum Machine Learning 19. Federated Quantum Natural Gradient Descent for Quantum Federated Learning 20. Mobile Computing Framework for Federated Learning 21. Federated Learning for Speech Recognition and Acoustic Processing
PART IV: Future Directions 22. Ethical Considerations and Legal Issues Relating to Federated Learning
