Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The process of FL.

Step 1: Server distributes the global model; Step 2: Clients train locally; Step 3: Clients upload the local model; Step 4: Server aggregates models.

More »

Fig 1 Expand

Fig 2.

Crossover operator.

More »

Fig 2 Expand

Fig 3.

Mutation operator.

More »

Fig 3 Expand

Table 1.

Hyper-parameter settings.

More »

Table 1 Expand

Fig 4.

The accuracy of MNIST dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 4 Expand

Fig 5.

The accuracy of FashionMNIST dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 5 Expand

Fig 6.

The accuracy of FashionMNIST dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 6 Expand

Fig 7.

The accuracy of MNIST dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 7 Expand

Fig 8.

The accuracy of FashionMNIST dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 8 Expand

Fig 9.

The accuracy of TodayNews dataset under FedAvg, FedProx, and SCAFFOLD.

More »

Fig 9 Expand

Table 2.

Comparison between methods with EA and methods without EA.

More »

Table 2 Expand

Table 3.

Impact of the hyperparameter μ.

More »

Table 3 Expand

Fig 10.

Comparison of MNIST with different intervals under FedAvg, FedProx and SCAFFOLD.

More »

Fig 10 Expand

Fig 11.

Comparison of TodayNew with different intervals under FedAvg, FedProx and SCAFFOLD.

More »

Fig 11 Expand

Fig 12.

Comparison of FashionMNIST with different intervals under FedAvg, FedProx and SCAFFOLD.

More »

Fig 12 Expand

Table 4.

Impact of the Dirichlet distribution.

More »

Table 4 Expand

Fig 13.

Visualization Comparison Between Client Model with NO_EA.

More »

Fig 13 Expand

Fig 14.

Visualization Comparison Between Client Model with EA.

More »

Fig 14 Expand

Table 5.

Comparison of model distances.

More »

Table 5 Expand