Edge-assisted Opportunistic Federated Learning for Distributed IoT systems

The paper introduces Opportunistic Federated Learning (OFL) as an approach to enhance the efficiency of distributed learning in intelligent IoT systems. OFL allows any node in the network to initiate a learning task and collabo- ratively use local resources. The framework enables nodes to adapt configurations based on circumstances, optimizing resource utilization. Hence, this paper proposes a reliable node selection mechanism that accommodates the dynamic nature of local data and computing resources. Incentives for participating nodes are explored through a peer-to-peer communication using the Bertrand game to determine optimal pricing strategies. Results demonstrate the Nash equilibrium of the game-based incentive mechanism in a realistic FL setup.