However, there is a clear trend of improvement and stabilization in the metrics as the number of rounds increases, culminating in an accuracy of 83.07% and a relatively high AUC of 92.41% in Round 5.
← all excerpts
APB-FLDPA: Adaptive Personalized Blockchain-Federated Learning With Differential Privacy and Attention for Privacy-Preserving Healthcare Analytics.
1
—
—