Server Averaging for Federated Learning

By George Pu, Yanlin Zhou, Dapeng Oliver Wu, Xiaolin Li. 2021

4 citations recorded by the source corpus.

Federated learning allows distributed devices to collectively train a model without sharing or disclosing the local dataset with a central server. The global model is optimized by training and averaging the model parameters of all local participants. However, the improved privacy of federated learning also introduces challenges including higher computation and communication costs. In particular, federated learning converges slower than centralized training. We propose the server averaging algorithm to accelerate convergence. Sever averaging constructs the shared global model by periodically averaging a set of previous global models. Our experiments indicate that server averaging not only converges faster, to a target accuracy, than federated averaging (FedAvg), but also reduces the computation costs on the client-level through epoch decay.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dapeng Oliver Wu
2. Xiyao Ma
3. Xiaolin Li
4. Yanlin Zhou
5. George Pu

Citations in the corpus

• Distilled One-Shot Federated Learning (2020, background): “Previous approaches try to learn faster when data is poorly distributed [25].”