quantum-federated-learning

This paper introduces a novel self-consistent midpoint aggregation method for stable quantum federated learning, addressing challenges like data heterogeneity and quantum noise with validation on real quantum machines.

This paper proposes DUQFL-Prox, a drift-stable quantum federated learning framework that uses deep-unfolded local optimization with adaptive SPSA updates and a proximal term to improve stability, generalization, and client fairness in heterogeneous distributed environments.