Fedmaj uses voting to pick best rules for federated learning
FedMaJ: Ordinal Meta-Aggregation for Federated Learning Using Majority-Judgment Voting
Networking and Internet Architecture
Summary
Federated learning helps many devices learn together without sharing their data. But the way these devices combine their learning updates often stays the same, even if conditions change. The authors introduce FedMaJ, which lets devices vote on which method to use for combining updates based on fairness, performance, and resources. Their tests show that this voting approach keeps learning stable and fair, even when conditions vary a lot.
What this means in practice
- •For federated learning engineers: Choose aggregation rules dynamically in federated learning systems to handle changing client and network conditions.
- •For wireless network operators: Improve fairness and resource efficiency in learning over wireless networks by adapting aggregation strategies based on client feedback.
Authors
Driss Choukri, Essaid Sabir, Halima Elbiaze, Abdelkrim Haqiq
Abstract
Federated learning traditionally relies on a fixed aggregation rule despite shifting client state and wireless dynamics. We present FedMaJ, a framework that dynamically selects aggregation rules via Majority Judgment voting. During voting rounds, clients evaluate candidate models across performance, resource utilization, channel condition, and fairness metrics. The server adopts the majority-preferred rule and retains it until the next vote, scheduled dynamically based on accuracy trends. Evaluated in over-the-air federated learning with explicit energy and resource cost modeling, synthetic and Fashion-MNIST experiments show that FedMaJ achieves competitive learning performance and superior aggregation-influence fairness. Under extreme-evaluation perturbations, Majority Judgment yields significantly more stable rule selections than mean-based scoring, establishing ordinal voting as a robust control layer for adaptive aggregation.