3.1.4. aijack.collaborative.fedexp package

3.1.4.1. Submodules

3.1.4.2. aijack.collaborative.fedexp.server module

class aijack.collaborative.fedexp.server.FedEXPServer(*args, eps=1e-05, **kwargs)

Bases: aijack.collaborative.fedavg.server.FedAVGServer

Implementation of ‘Jhunjhunwala, Divyansh, Shiqiang Wang, and Gauri Joshi. “FedExP: Speeding up Federated Averaging Via Extrapolation.” arXiv preprint arXiv:2301.09604 (2023).’

update(*args, **kwargs)

Update the global model

Parameters

use_gradients (bool, optional) – If True, update the global model with aggregated local gradients. Defaults to True.

update_from_gradients()

Update the global model with the local gradients.

3.1.4.3. Module contents