Machine Learning Security & Autonomous Driving

Federated learning is a learning method that collects only learned models on a server to ensure data privacy. FL proceeds with data directly from distributed clients. As clients in FL often have limited communication bandwidth, communication between servers and clients should be optimized to improve performance. FL clients have to communicate in unstable network environments. However, as existing FL aggregation algorithms transmit and receive a large amount of weights, accuracy is significantly reduced in unstable network environments.