most citedLocal-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data

36 citations · 49 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2021★ 13 cited

FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization

Dezhong Yao, Wanning Pan, Michael J O'Neill +4

One underlying assumption of recent federated learning (FL) paradigms is that all local models usually share the same network architecture and size, which becomes impractical for d…

cs.LG2021★ 36 cited

Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data

Dezhong Yao, Wanning Pan, Yutong Dai +5

Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, du…