most citedEfficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability

2 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2026

Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning

Ming Xiang, Stratis Ioannidis, Edmund Yeh +2

Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dyna…

cs.DC2024★ 2 cited

Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability

Ming Xiang, Stratis Ioannidis, Edmund Yeh +2

Addressing intermittent client availability is critical for the real-world deployment of federated learning algorithms. Most prior work either overlooks the potential non-stationar…