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

<div>Accuracy curves of WCL under QUIC dataset with 50 clients and the selected client ratio set to 0.3 in two different data distribution situations: (a) high data heterogeneity and (b) low data heterogeneity.</div>

Wireless Communications and Mobile Computing

fig5

Figure 5

Figure 5: WCL: Client Selection in Federated Learning with a Combination of Model Weight Divergence and Client Training Loss for Internet Traffic Classification 

Figure 5 | WCL: Client Selection in Federated Learning with a Combination of Model Weight Divergence and Client Training Loss for Internet Traffic Classification 