Federated learning
Qiang Yang (Author), Yang Liu (Author), Yong Cheng (Author), Yan Kang (Author), Tianjian Chen (Author), Han Yu (Author)
How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union's General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application
1 online resource (xvii, 189 pages) : illustrations (some color).
9781681736983, 9783031015854, 1681736985, 3031015851
1133126613
Print version:
1. Introduction
1.1. Motivation
1.2. Federated learning as a solution
1.3. Current development in federated learning
1.4. Organization of this book 2. Background
2.1. Privacy-preserving machine learning
2.2. PPML and secure ML
2.3. Threat and security models
2.4. Privacy preservation techniques 3. Distributed machine learning
3.1. Introduction to DML
3.2. Scalability-motivated DML
3.3. Privacy-motivated DML
3.4. Privacy-preserving gradient descent
3.5. Summary 4. Horizontal federated learning
4.1. The definition of HFL
4.2. Architecture of HFL
4.3. The federated averaging algorithm
4.4. improvement of the FedAvg algorithm
4.5. Related works
4.6. Challenges and outlook 5. Vertical federated learning
5.1. The definition of VFL
5.2. Architecture of VFL
5.3. Algorithms of VFL
5.4. Challenges and outlook 6. Federated transfer learning
6.1. Heterogeneous federated learning
6.2. federated transfer learning
6.3. The FTL framework
6.4. Challenges and outlook 7. Incentive mechanism design for federated learning
7.1. Paying for contributions
7.2. A fairness-aware profit sharing framework
7.3. Discussions 8. Federated learning for vision, language, and recommendation
8.1. Federated learning for computer vision
8.2. Federated Learning for NLP
8.3. Federated learning for recommendation systems 9. Federated reinforcement learning
9.1. Introduction to reinforcement learning
9.2. Reinforcement learning algorithms
9.3. Distributed reinforcement learning
9.4. Federated reinforcement learning
9.5. Challenges and outlook 10. Selected applications
10.1. Finance
10.2. Healthcare
10.3. Education
10.4. Urban computing and smart city
10.5. Edge computing and internet of things
10.6. Blockchain
10.7. 5G mobile networks 11. Summary and outlook
A. Legal development on data protection
A.1. Data protection in the European Union
A.2. Data protection in the USA
A.3. Data protection in China