Figure 2
From: Semi-decentralized federated learning with client pairing for efficient mutual knowledge transfer
The structure of the proposed DKT-CP method. Each number corresponds to a specific step: 1. sharing data distribution information, 2. computing the KLD matrix, 3. pairing clients based on the KLD matrix, 4. assigning roles to clients: local update, DML aggregation, or dormant, 5. local update, 6. DML aggregation.
