← Search

Yuanxiong Guo

2 accepted papers

2022

Hybrid Local SGD for Federated Learning with Heterogeneous Communications

ICLR 2022spotlight

Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data. While local SGD has been proposed to reduce the number of FL rounds and become the algorithm…

Cited by 60SourcePDFScholar
2021

Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

IJCAI 2021poster

Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarante…

Cited by 59SourcePDFScholar