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.

Communication between the clients and the server under FedAvg.

More »

Fig 1 Expand

Fig 2.

FedAvg complemented by the data-sharing strategy: Distribute shared data to the clients at initialization.

More »

Fig 2 Expand

Fig 3.

Communication between the clients and the server under LoAdaBoost FedAvg.

More »

Fig 3 Expand

Table 1.

Summary of the evaluation dataset.

More »

Table 1 Expand

Table 2.

Example rows and columns of DRUGS.

More »

Table 2 Expand

Fig 4.

Performance gap between IID and non-IID data.

More »

Fig 4 Expand

Fig 5.

Comparison of FedAvg and LoAdaboost on IID data.

LoAdaBoost converged slightly slower than FedAvg, but to a higher test AUC.

More »

Fig 5 Expand

Table 3.

IID scenario: 10-fold cross validation results with varying C and E.

More »

Table 3 Expand

Fig 6.

Comparison of FedAvg and LoAdaboost on non-IID data with data-sharing strategy.

More »

Fig 6 Expand

Table 4.

Non-IID scenario: 10-fold cross validation results with varying α and β.

More »

Table 4 Expand

Table 5.

Non-IID scenario: 10-fold cross validation results with varying C.

More »

Table 5 Expand

Table 6.

Summary of the eICU dataset.

More »

Table 6 Expand

Fig 7.

Comparison of FedAvg and LoAdaboostFedAvg on eICU data.

More »

Fig 7 Expand

Table 7.

Evaluation on eICU data: 10-fold cross validation results.

More »

Table 7 Expand