IEEE

TaiChi: Efficient Execution for Multi-DNNs Using Graph-Based Scheduling

Abstract: Applications constructed with multiple Deep Neural Networks (multi-DNNs) are growing rapidly in edge and data center. However, executing multi-DNNs efficiently remains chal-lenging because ...
IEEE

Detection of Malicious Clients in Federated Learning Using Graph Neural Network

Abstract: Federated Learning (FL) facilitates decentralized model training without the exchange of raw data, thereby guaranteeing privacy. However, due to its distributed nature, this paradigm is ...