3.1.9. aijack.collaborative.moon package#

3.1.9.1. Submodules#

3.1.9.2. aijack.collaborative.moon.client module#

class aijack.collaborative.moon.client.MOONClient(model, mu=0.1, tau=1.0, **kwargs)[source]#

Bases: aijack.collaborative.fedavg.client.FedAVGClient

Client of MOON for single process simulation (Li, Qinbin, Bingsheng He, and Dawn Song. “Model-contrastive federated learning.” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.)

Parameters

  • model (torch.nn.Module) – local model

  • mu (float) – weight of model-contrastive loss

  • tau (float) – tempreature within model-contrastive loss

local_train(local_epoch, criterion, trainloader, optimizer, communication_id=0)[source]#

3.1.9.3. Module contents#

class aijack.collaborative.moon.MOONClient(model, mu=0.1, tau=1.0, **kwargs)[source]#

Bases: aijack.collaborative.fedavg.client.FedAVGClient

Client of MOON for single process simulation (Li, Qinbin, Bingsheng He, and Dawn Song. “Model-contrastive federated learning.” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.)

Parameters

  • model (torch.nn.Module) – local model

  • mu (float) – weight of model-contrastive loss

  • tau (float) – tempreature within model-contrastive loss

local_train(local_epoch, criterion, trainloader, optimizer, communication_id=0)[source]#