A2G-QFL: Adaptive Aggregation with Two Gains in Quantum Federated learning
This addresses performance issues in quantum federated learning systems, which is an incremental improvement over classical aggregation methods.
The paper tackles performance degradation in quantum federated learning due to client heterogeneity and quantum noise by introducing A2G, a dual-gain aggregation framework that jointly regulates geometric blending and client importance. Experiments on a hybrid testbed show improved stability and higher accuracy under heterogeneous and noisy conditions.
Federated learning (FL) deployed over quantum enabled and heterogeneous classical networks faces significant performance degradation due to uneven client quality, stochastic teleportation fidelity, device instability, and geometric mismatch between local and global models. Classical aggregation rules assume euclidean topology and uniform communication reliability, limiting their suitability for emerging quantum federated systems. This paper introduces A2G (Adaptive Aggregation with Two Gains), a dual gain framework that jointly regulates geometric blending through a geometry gain and modulates client importance using a QoS gain derived from teleportation fidelity, latency, and instability. We develop the A2G update rule, establish convergence guarantees under smoothness and bounded variance assumptions, and show that A2G recovers FedAvg, QoS aware averaging, and manifold based aggregation as special cases. Experiments on a quantum classical hybrid testbed demonstrate improved stability and higher accuracy under heterogeneous and noisy conditions.