Balancing Data Privacy and 5G VNFs Security Monitoring: Federated Learning with CNN + BiLSTM + LSTM Model

Table 4

Optimal hyperparameters for FL and CL with the InSDN dataset.

Parameters	Federated learning	Centralized learning
Learning rate	0.0015	0.01
Number of rounds	8	—
Number of epochs	5	20
Batch size	128	128
Number of clients	3, 6, 9, 12	—
Loss function	Adam	Adam