Efficient privacy-preserving ML for IoT: Cluster-based split federated learning scheme for non-IID data

Keyphrases

• Client Data 20%
• Client Resources 20%
• Client Selection 20%
• Cluster-based 100%
• Clustering Scheme 20%
• Data Distribution 20%
• Distributed Machine Learning 20%
• Fast Training 20%
• Federated Learning 60%
• FL Performance 20%
• Forced Synchronization 20%
• Genetic Algorithm 20%
• Identically Distributed 20%
• IoT Cluster 100%
• IoT Devices 20%
• IoT Environment 20%
• Learning Scheme 100%
• Limited Resources 20%
• Machine Learning Training 20%
• Neural Network Model 20%
• Non-independent and Identically Distributed Data 100%
• Parallelization 20%
• Privacy-Preserving ML 100%
• Resource Availability 20%
• Resource Capability 20%
• Split Federated Learning 100%
• Split Learning 100%
• Stragglers 20%
• Training Model 20%
• Two-stage Clustering 20%
• User Privacy 20%
• Weak Devices 20%

Computer Science

• Clustering Scheme 25%
• Data Distribution 25%
• Distributed Client 25%
• Distributed Machine Learning 25%
• Federated machine learning 100%
• Genetic Algorithm 25%
• Internet-Of-Things 100%
• Learning Scheme 100%
• Machine Learning 100%
• Multiobjective 25%
• Neural Network Model 25%
• Parallelism 25%
• Privacy Preserving 100%
• Resource Availability 25%
• Resource-Client 25%
• Synchronism 25%
• Training Model 25%
• User Privacy 25%