Yao Sun, PhD, is a Lecturer with the University of Glasgow in the United Kingdom. He was a former Research Fellow at UESTC in Chengdu, China. Chaoqun You is a Research Fellow at the Singapore University of Technology and Design. She was formerly an Academic Guest with the Department of Electronic Computer Engineering at the University of Toronto. Gang Feng is a Professor at the University of Electronic Science and Technology of China. He was an Associate Professor at Nanyang Technological University. Lei Zhang, PhD, is a Professor at the University of Glasgow, UK. He was formerly a Research Fellow at the 5G Innovation Centre at the University of Surrey.

• About the Editors xvPreface xvii1 Federated Learning with Unreliable Transmission in Mobile Edge Computing Systems 1Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Howard H. Yang, and Tony Q. S. Quek1.1 System Model 11.2 Problem Formulation 41.3 A Joint Optimization Algorithm 101.4 Simulation and Experiment Results 162 Federated Learning with non-IID data in Mobile Edge Computing Systems 23Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Geyong Min, and Hancong Duan2.1 System Model 232.2 Performance Analysis and Averaging Design 242.3 Data Sharing Scheme 302.4 Simulation Results 423 How Many Resources Are Needed to Support Wireless Edge Networks 49Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin3.1 Introduction 493.2 System Model 503.3 Wireless Bandwidth and Computing Resources Consumed for Supporting FL-EnabledWireless Edge Networks 543.4 The Relationship between FL Performance and Consumed Resources 593.5 Discussions of Three Cases 623.6 Numerical Results and Discussion 673.7 Conclusion 753.8 Proof of Corollary 3.2 763.9 Proof of Corollary 3.3 774 Device Association Based on Federated Deep Reinforcement Learning for Radio Access Network Slicing 85Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin4.1 Introduction 854.2 System Model 874.3 Problem Formulation 904.4 Hybrid Federated Deep Reinforcement Learning for Device Association 944.5 Numerical Results 1034.6 Conclusion 1095 Deep Federated Learning Based on Knowledge Distillation and Differential Privacy 113Hui Lin, Feng Yu, and Xiaoding Wang5.1 Introduction 1135.2 RelatedWork 1155.3 System Model 1185.4 The Implementation Details of the Proposed Strategy 1195.5 Performance Evaluation 1205.6 Conclusions 1226 Federated Learning-Based Beam Management in Dense Millimeter Wave Communication Systems 127Qing Xue and Liu Yang6.1 Introduction 1276.2 System Model 1306.3 Problem Formulation and Analysis 1336.4 FL-Based Beam Management in UDmmN 1356.6 Conclusions 1507 Blockchain-Empowered Federated Learning Approach for An Intelligent and Reliable D2D Caching Scheme 155Runze Cheng, Yao Sun, Yijing Liu, Le Xia, Daquan Feng, and Muhammad Imran7.1 Introduction 1557.2 RelatedWork 1577.3 System Model 1597.4 Problem Formulation and DRL-Based Model Training 1607.5 Privacy-Preserved and Secure BDRFL Caching Scheme Design 1657.6 Consensus Mechanism and Federated Learning Model Update 1707.7 Simulation Results and Discussions 1737.8 Conclusion 1778 Heterogeneity-Aware Dynamic Scheduling for Federated Edge Learning 181Kun Guo, Zihan Chen, Howard H. Yang, and Tony Q. S. Quek8.1 Introduction 1818.2 RelatedWorks 1848.3 System Model for FEEL 1858.4 Heterogeneity-Aware Dynamic Scheduling Problem Formulation 1898.5 Dynamic Scheduling Algorithm Design and Analysis 1928.6 Evaluation Results 1978.7 Conclusions 2088.A.1 Proof of Theorem 8.2 2088.A.2 Proof of Theorem 8.3 2099 Robust Federated Learning with Real-World Noisy Data 215Jingyi Xu, Zihan Chen, Tony Q. S. Quek, and Kai Fong Ernest Chong9.1 Introduction 2159.2 RelatedWork 2179.3 FedCorr 2199.4 Experiments 2269.5 Further Remarks 23210 Analog Over-the-Air Federated Learning: Design and Analysis 239Howard H. Yang, Zihan Chen, and Tony Q. S. Quek10.1 Introduction 23910.2 System Model 24110.3 Analog Over-the-Air Model Training 24210.4 Convergence Analysis 24510.5 Numerical Results 25010.6 Conclusion 25311 Federated Edge Learning for Massive MIMO CSI Feedback 257Shi Jin, Yiming Cui, and Jiajia Guo11.1 Introduction 25711.2 System Model 25911.3 FEEL for DL-Based CSI Feedback 26011.4 Simulation Results 26411.5 Conclusion 26812 User-Centric Decentralized Federated Learning for Autoencoder-Based CSI Feedback 273Shi Jin, Jiajia Guo, Yan Lv, and Yiming Cui12.1 Autoencoder-Based CSI Feedback 27312.2 User-Centric Online Training for AE-Based CSI Feedback 27512.3 Multiuser Online Training Using Decentralized Federated Learning 27912.4 Numerical Results 28312.5 Conclusion 287Bibliography 287Index 291

Yao Sun, PhD, is a Lecturer with the University of Glasgow in the United Kingdom. He was a former Research Fellow at UESTC in Chengdu, China. Chaoqun You is a Research Fellow at the Singapore University of Technology and Design. She was formerly an Academic Guest with the Department of Electronic Computer Engineering at the University of Toronto. Gang Feng is a Professor at the University of Electronic Science and Technology of China. He was an Associate Professor at Nanyang Technological University. Lei Zhang, PhD, is a Professor at the University of Glasgow, UK. He was formerly a Research Fellow at the 5G Innovation Centre at the University of Surrey.

• About the Editors xvPreface xvii1 Federated Learning with Unreliable Transmission in Mobile Edge Computing Systems 1Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Howard H. Yang, and Tony Q. S. Quek1.1 System Model 11.2 Problem Formulation 41.3 A Joint Optimization Algorithm 101.4 Simulation and Experiment Results 162 Federated Learning with non-IID data in Mobile Edge Computing Systems 23Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Geyong Min, and Hancong Duan2.1 System Model 232.2 Performance Analysis and Averaging Design 242.3 Data Sharing Scheme 302.4 Simulation Results 423 How Many Resources Are Needed to Support Wireless Edge Networks 49Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin3.1 Introduction 493.2 System Model 503.3 Wireless Bandwidth and Computing Resources Consumed for Supporting FL-EnabledWireless Edge Networks 543.4 The Relationship between FL Performance and Consumed Resources 593.5 Discussions of Three Cases 623.6 Numerical Results and Discussion 673.7 Conclusion 753.8 Proof of Corollary 3.2 763.9 Proof of Corollary 3.3 774 Device Association Based on Federated Deep Reinforcement Learning for Radio Access Network Slicing 85Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin4.1 Introduction 854.2 System Model 874.3 Problem Formulation 904.4 Hybrid Federated Deep Reinforcement Learning for Device Association 944.5 Numerical Results 1034.6 Conclusion 1095 Deep Federated Learning Based on Knowledge Distillation and Differential Privacy 113Hui Lin, Feng Yu, and Xiaoding Wang5.1 Introduction 1135.2 RelatedWork 1155.3 System Model 1185.4 The Implementation Details of the Proposed Strategy 1195.5 Performance Evaluation 1205.6 Conclusions 1226 Federated Learning-Based Beam Management in Dense Millimeter Wave Communication Systems 127Qing Xue and Liu Yang6.1 Introduction 1276.2 System Model 1306.3 Problem Formulation and Analysis 1336.4 FL-Based Beam Management in UDmmN 1356.6 Conclusions 1507 Blockchain-Empowered Federated Learning Approach for An Intelligent and Reliable D2D Caching Scheme 155Runze Cheng, Yao Sun, Yijing Liu, Le Xia, Daquan Feng, and Muhammad Imran7.1 Introduction 1557.2 RelatedWork 1577.3 System Model 1597.4 Problem Formulation and DRL-Based Model Training 1607.5 Privacy-Preserved and Secure BDRFL Caching Scheme Design 1657.6 Consensus Mechanism and Federated Learning Model Update 1707.7 Simulation Results and Discussions 1737.8 Conclusion 1778 Heterogeneity-Aware Dynamic Scheduling for Federated Edge Learning 181Kun Guo, Zihan Chen, Howard H. Yang, and Tony Q. S. Quek8.1 Introduction 1818.2 RelatedWorks 1848.3 System Model for FEEL 1858.4 Heterogeneity-Aware Dynamic Scheduling Problem Formulation 1898.5 Dynamic Scheduling Algorithm Design and Analysis 1928.6 Evaluation Results 1978.7 Conclusions 2088.A.1 Proof of Theorem 8.2 2088.A.2 Proof of Theorem 8.3 2099 Robust Federated Learning with Real-World Noisy Data 215Jingyi Xu, Zihan Chen, Tony Q. S. Quek, and Kai Fong Ernest Chong9.1 Introduction 2159.2 RelatedWork 2179.3 FedCorr 2199.4 Experiments 2269.5 Further Remarks 23210 Analog Over-the-Air Federated Learning: Design and Analysis 239Howard H. Yang, Zihan Chen, and Tony Q. S. Quek10.1 Introduction 23910.2 System Model 24110.3 Analog Over-the-Air Model Training 24210.4 Convergence Analysis 24510.5 Numerical Results 25010.6 Conclusion 25311 Federated Edge Learning for Massive MIMO CSI Feedback 257Shi Jin, Yiming Cui, and Jiajia Guo11.1 Introduction 25711.2 System Model 25911.3 FEEL for DL-Based CSI Feedback 26011.4 Simulation Results 26411.5 Conclusion 26812 User-Centric Decentralized Federated Learning for Autoencoder-Based CSI Feedback 273Shi Jin, Jiajia Guo, Yan Lv, and Yiming Cui12.1 Autoencoder-Based CSI Feedback 27312.2 User-Centric Online Training for AE-Based CSI Feedback 27512.3 Multiuser Online Training Using Decentralized Federated Learning 27912.4 Numerical Results 28312.5 Conclusion 287Bibliography 287Index 291

Yao Sun, PhD, is a Lecturer with the University of Glasgow in the United Kingdom. He was a former Research Fellow at UESTC in Chengdu, China. Chaoqun You is a Research Fellow at the Singapore University of Technology and Design. She was formerly an Academic Guest with the Department of Electronic Computer Engineering at the University of Toronto. Gang Feng is a Professor at the University of Electronic Science and Technology of China. He was an Associate Professor at Nanyang Technological University. Lei Zhang, PhD, is a Professor at the University of Glasgow, UK. He was formerly a Research Fellow at the 5G Innovation Centre at the University of Surrey.

• About the Editors xvPreface xvii1 Federated Learning with Unreliable Transmission in Mobile Edge Computing Systems 1Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Howard H. Yang, and Tony Q. S. Quek1.1 System Model 11.2 Problem Formulation 41.3 A Joint Optimization Algorithm 101.4 Simulation and Experiment Results 162 Federated Learning with non-IID data in Mobile Edge Computing Systems 23Chenyuan Feng, Daquan Feng, Zhongyuan Zhao, Geyong Min, and Hancong Duan2.1 System Model 232.2 Performance Analysis and Averaging Design 242.3 Data Sharing Scheme 302.4 Simulation Results 423 How Many Resources Are Needed to Support Wireless Edge Networks 49Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin3.1 Introduction 493.2 System Model 503.3 Wireless Bandwidth and Computing Resources Consumed for Supporting FL-EnabledWireless Edge Networks 543.4 The Relationship between FL Performance and Consumed Resources 593.5 Discussions of Three Cases 623.6 Numerical Results and Discussion 673.7 Conclusion 753.8 Proof of Corollary 3.2 763.9 Proof of Corollary 3.3 774 Device Association Based on Federated Deep Reinforcement Learning for Radio Access Network Slicing 85Yi-Jing Liu, Gang Feng, Yao Sun, and Shuang Qin4.1 Introduction 854.2 System Model 874.3 Problem Formulation 904.4 Hybrid Federated Deep Reinforcement Learning for Device Association 944.5 Numerical Results 1034.6 Conclusion 1095 Deep Federated Learning Based on Knowledge Distillation and Differential Privacy 113Hui Lin, Feng Yu, and Xiaoding Wang5.1 Introduction 1135.2 RelatedWork 1155.3 System Model 1185.4 The Implementation Details of the Proposed Strategy 1195.5 Performance Evaluation 1205.6 Conclusions 1226 Federated Learning-Based Beam Management in Dense Millimeter Wave Communication Systems 127Qing Xue and Liu Yang6.1 Introduction 1276.2 System Model 1306.3 Problem Formulation and Analysis 1336.4 FL-Based Beam Management in UDmmN 1356.6 Conclusions 1507 Blockchain-Empowered Federated Learning Approach for An Intelligent and Reliable D2D Caching Scheme 155Runze Cheng, Yao Sun, Yijing Liu, Le Xia, Daquan Feng, and Muhammad Imran7.1 Introduction 1557.2 RelatedWork 1577.3 System Model 1597.4 Problem Formulation and DRL-Based Model Training 1607.5 Privacy-Preserved and Secure BDRFL Caching Scheme Design 1657.6 Consensus Mechanism and Federated Learning Model Update 1707.7 Simulation Results and Discussions 1737.8 Conclusion 1778 Heterogeneity-Aware Dynamic Scheduling for Federated Edge Learning 181Kun Guo, Zihan Chen, Howard H. Yang, and Tony Q. S. Quek8.1 Introduction 1818.2 RelatedWorks 1848.3 System Model for FEEL 1858.4 Heterogeneity-Aware Dynamic Scheduling Problem Formulation 1898.5 Dynamic Scheduling Algorithm Design and Analysis 1928.6 Evaluation Results 1978.7 Conclusions 2088.A.1 Proof of Theorem 8.2 2088.A.2 Proof of Theorem 8.3 2099 Robust Federated Learning with Real-World Noisy Data 215Jingyi Xu, Zihan Chen, Tony Q. S. Quek, and Kai Fong Ernest Chong9.1 Introduction 2159.2 RelatedWork 2179.3 FedCorr 2199.4 Experiments 2269.5 Further Remarks 23210 Analog Over-the-Air Federated Learning: Design and Analysis 239Howard H. Yang, Zihan Chen, and Tony Q. S. Quek10.1 Introduction 23910.2 System Model 24110.3 Analog Over-the-Air Model Training 24210.4 Convergence Analysis 24510.5 Numerical Results 25010.6 Conclusion 25311 Federated Edge Learning for Massive MIMO CSI Feedback 257Shi Jin, Yiming Cui, and Jiajia Guo11.1 Introduction 25711.2 System Model 25911.3 FEEL for DL-Based CSI Feedback 26011.4 Simulation Results 26411.5 Conclusion 26812 User-Centric Decentralized Federated Learning for Autoencoder-Based CSI Feedback 273Shi Jin, Jiajia Guo, Yan Lv, and Yiming Cui12.1 Autoencoder-Based CSI Feedback 27312.2 User-Centric Online Training for AE-Based CSI Feedback 27512.3 Multiuser Online Training Using Decentralized Federated Learning 27912.4 Numerical Results 28312.5 Conclusion 287Bibliography 287Index 291