WCL: Client Selection in Federated Learning with a Combination of Model Weight Divergence and Client Training Loss for Internet Traffic Classification

Table 1

Definition of notations.

Symbol	Description
	Candidate client set
	Selected client set
	Global model obtained in round
	The th client model in round
	Client learning rate in round
	Gradient function
	Weight divergence of the th selected clients in round
	Client training loss of the th selected clients in round
	Priority value of the th selected clients in round
	The selected client ratio