FL-QDSNNs: Federated Learning with Quantum Dynamic Spiking Neural Networks

TL;DR

FL-QDSNNs introduces a privacy-preserving federated learning framework utilizing dynamic-threshold quantum spiking neural networks, effectively handling non-IID data and maintaining high accuracy across multiple clients.

Contribution

The paper proposes a novel quantum spiking neural network model with dynamic thresholds for federated learning, enhancing expressiveness and efficiency in privacy-sensitive, heterogeneous data environments.

Findings

Achieves 94% accuracy on Iris dataset

Outperforms state-of-the-art quantum federated baselines

Maintains high performance with up to 25 clients

Abstract

We present Federated Learning-Quantum Dynamic Spiking Neural Networks (FL-QDSNNs), a privacy-preserving framework that maintains high predictive accuracy on non-IID client data. Its key innovation is a dynamic-threshold spiking mechanism that triggers quantum gates only when local data drift requires added expressiveness, limiting circuit depth and countering the accuracy loss typical of heterogeneous clients. Evaluated on different benchmark datasets, including Iris, where FL-QDSNNs reach 94% accuracy, the approach consistently surpasses state-of-the-art quantum-federated baselines; scaling analyses demonstrate that performance remains high as the federation expands to 25 clients, confirming both computational efficiency and collaboration robustness. By uniting adaptive quantum expressiveness with strict data locality, FL-QDSNNs enable regulation-compliant quantum learning for privacy-sensitive sectors and critical infrastructure.