IEEE

Noise-Robust Federated Learning With Model Heterogeneous Clients

Abstract: Federated Learning (FL) enables multiple devices to collaboratively train models without sharing their raw data. Considering that clients may prefer to design their own models independently, ...
IEEE

Joint Client and Cross-Client Edge Selection for Cost-Efficient Federated Learning of Graph Convolutional Networks

Abstract: Graph-structured data applications promote the development of Graph Neural Networks (GNN) in recent years. Due to privacy concerns, collecting graph data stored in massive client devices for ...