Table 3.

Saturated performances of stochastic channel-based federated learning (SCBFL) and federated averaging (FA) with and without pruning.

Methods	AUC-ROCa	AUC-PRb
FA	0.9821	0.9731
SCBFL	0.9825	0.9763
FAwPc	0.9809	0.9683
SCBFLwPd	0.9776	0.9694

^aAUC-ROC: area under the receiver operating characteristic curve.

^bAUC-PR: area under the precision-recall curve.

^cFAwP: federating averaging with pruning.

^dSCBFLwP: stochastic channel-based federated learning with pruning.