Federated Learning: Theory and Practice provides a holistic treatment to federated learning, starting with a broad overview on federated learning as a distributed learning system with various forms of decentralized data and features. A detailed exposition then follows of core challenges and practical modeling techniques and solutions, spanning a variety of aspects in communication efficiency, theoretical convergence and security, viewed from different perspectives. Part II features emerging challenges stemming from many socially driven concerns of federated learning as a future public machine learning service, and Part III and IV present a wide array of industrial applications of federated learning, including potential venues and visions for federated learning in the near future. This book provides a comprehensive and accessible introduction to federated learning which is suitable for researchers and students in academia and industrial practitioners who seek to leverage the latest advances in machine learning for their entrepreneurial endeavors
1. 1.1 Introduction - p. page3 2. 1.2 Basic components of GD-type methods - p. 5 3. 1.3 Stochastic gradient descent methods - p. 19 4. 1.4 Concluding remarks - p. 24 5. References - p. page25 6. Chapter 2. Considerations on the theory of training models with differential privacy - p. 29 7. Chapter 3. Privacy-preserving federated learning: algorithms and guarantees - p. 57 8. Chapter 4. Assessing vulnerabilities and securing federated learning - p. 75 9. Chapter 5. Adversarial robustness in federated learning - p. 91 10. Chapter 6. Evaluating gradient inversion attacks and defenses - p. 105 11. Part 2: Emerging topics - p. 122 12. Chapter 7. Personalized federated learning: theory and open problems - p. 125 13. Chapter 8. Fairness in federated learning - p. 143 14. Chapter 9. Meta-federated learning - p. 161 15. Chapter 10. Graph-aware federated learning - p. 181 16. Chapter 11. Vertical asynchronous federated learning: algorithms and theoretic guarantees - p. 199 17. Chapter 12. Hyperparameter tuning for federated learning – systems and practices - p. 219 18. Chapter 13. Hyper-parameter optimization in federated learning - p. 237 19. Chapter 14. Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond - p. 257 20. Chapter 15. Data valuation in federated learning - p. 281 21. Part 3: Applications & ethical considerations - p. 296 22. Chapter 16. Incentives in federated learning - p. 299 23. Chapter 17. Introduction to quantum federated machine learning - p. 311 24. Chapter 18. Federated quantum natural gradient descent for quantum federated learning - p. 329 25. Chapter 19. Mobile computing framework for federated learning - p. 343 26. Chapter 20. Federated learning for privacy-preserving speech recognition - p. 353 27. Chapter 21. Ethical considerations and legal issues relating to federated learning - p. 388 28. Index - p. 393
Federated Learning: Theory and Practice provides a holistic treatment to federated learning, starting with a broad overview on federated learning as a distributed learning system with various forms of decentralized data and features. A detailed exposition then follows of core challenges and practical modeling techniques and solutions, spanning a variety of aspects in communication efficiency, theoretical convergence and security, viewed from different perspectives. Part II features emerging challenges stemming from many socially driven concerns of federated learning as a future public machine learning service, and Part III and IV present a wide array of industrial applications of federated learning, including potential venues and visions for federated learning in the near future. This book provides a comprehensive and accessible introduction to federated learning which is suitable for researchers and students in academia and industrial practitioners who seek to leverage the latest advances in machine learning for their entrepreneurial endeavors
1. 1.1 Introduction - p. page3 2. 1.2 Basic components of GD-type methods - p. 5 3. 1.3 Stochastic gradient descent methods - p. 19 4. 1.4 Concluding remarks - p. 24 5. References - p. page25 6. Chapter 2. Considerations on the theory of training models with differential privacy - p. 29 7. Chapter 3. Privacy-preserving federated learning: algorithms and guarantees - p. 57 8. Chapter 4. Assessing vulnerabilities and securing federated learning - p. 75 9. Chapter 5. Adversarial robustness in federated learning - p. 91 10. Chapter 6. Evaluating gradient inversion attacks and defenses - p. 105 11. Part 2: Emerging topics - p. 122 12. Chapter 7. Personalized federated learning: theory and open problems - p. 125 13. Chapter 8. Fairness in federated learning - p. 143 14. Chapter 9. Meta-federated learning - p. 161 15. Chapter 10. Graph-aware federated learning - p. 181 16. Chapter 11. Vertical asynchronous federated learning: algorithms and theoretic guarantees - p. 199 17. Chapter 12. Hyperparameter tuning for federated learning – systems and practices - p. 219 18. Chapter 13. Hyper-parameter optimization in federated learning - p. 237 19. Chapter 14. Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond - p. 257 20. Chapter 15. Data valuation in federated learning - p. 281 21. Part 3: Applications & ethical considerations - p. 296 22. Chapter 16. Incentives in federated learning - p. 299 23. Chapter 17. Introduction to quantum federated machine learning - p. 311 24. Chapter 18. Federated quantum natural gradient descent for quantum federated learning - p. 329 25. Chapter 19. Mobile computing framework for federated learning - p. 343 26. Chapter 20. Federated learning for privacy-preserving speech recognition - p. 353 27. Chapter 21. Ethical considerations and legal issues relating to federated learning - p. 388 28. Index - p. 393
