FairEnergy: Contribution-Based Fairness meets Energy Efficiency in Federated Learning
By: Ouiame Marnissi, Hajar EL Hammouti, El Houcine Bergou
Potential Business Impact:
Saves phone battery while learning together.
Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy. However, balancing energy efficiency and fair participation while ensuring high model accuracy remains challenging in wireless edge systems due to heterogeneous resources, unequal client contributions, and limited communication capacity. To address these challenges, we propose FairEnergy, a fairness-aware energy minimization framework that integrates a contribution score capturing both the magnitude of updates and their compression ratio into the joint optimization of device selection, bandwidth allocation, and compression level. The resulting mixed-integer non-convex problem is solved by relaxing binary selection variables and applying Lagrangian decomposition to handle global bandwidth coupling, followed by per-device subproblem optimization. Experiments on non-IID data show that FairEnergy achieves higher accuracy while reducing energy consumption by up to 79\% compared to baseline strategies.
Similar Papers
Federated Learning within Global Energy Budget over Heterogeneous Edge Accelerators
Distributed, Parallel, and Cluster Computing
Trains AI smarter with less energy.
Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design
Machine Learning (CS)
Makes smart cameras learn faster and use less power.
Energy-Efficient Quantized Federated Learning for Resource-constrained IoT devices
Machine Learning (CS)
Saves energy for smart devices learning together.