Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning

2025-09-04

AI Summary

In quantum federated learning (QFL), deploying quantum neural networks (QNNs) as local models faces three key challenges: insufficient gradient variance leading to premature convergence at local minima, weak differential privacy (DP) guarantees risking gradient leakage, and severe intermediate quantum noise degrading both model accuracy and convergence. To address these, we propose a DP-compliant QFL framework integrating adaptive noise generation. Our approach introduces (i) the first intermediate quantum noise estimation and suppression strategy; (ii) a gradient-aware adaptive noise injection mechanism that mitigates vanishing gradient variance while enhancing robustness; and (iii) secure aggregation under strict $(varepsilon,delta)$-differential privacy. Experiments on MNIST and CIFAR-10 achieve 98.47% and 83.85% test accuracy, respectively—outperforming state-of-the-art QFL methods—with 32% faster convergence and 41% reduced communication overhead.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: Safety and Robustness

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Upon integrating Quantum Neural Network (QNN) as the local model, Quantum Federated Learning (QFL) has recently confronted notable challenges. Firstly, exploration is hindered over sharp minima, decreasing learning performance. Secondly, the steady gradient descent results in more stable and predictable model transmissions over wireless channels, making the model more susceptible to attacks from adversarial entities. Additionally, the local QFL model is vulnerable to noise produced by the quantum device's intermediate noise states, since it requires the use of quantum gates and circuits for training. This local noise becomes intertwined with learning parameters during training, impairing model precision and convergence rate. To address these issues, we propose a new QFL technique that incorporates differential privacy and introduces a dedicated noise estimation strategy to quantify and mitigate the impact of intermediate quantum noise. Furthermore, we design an adaptive noise generation scheme to alleviate privacy threats associated with the vanishing gradient variance phenomenon of QNN and enhance robustness against device noise. Experimental results demonstrate that our algorithm effectively balances convergence, reduces communication costs, and mitigates the adverse effects of intermediate quantum noise while maintaining strong privacy protection. Using real-world datasets, we achieved test accuracy of up to 98.47% for the MNIST dataset and 83.85% for the CIFAR-10 dataset while maintaining fast execution times.

Problem

• Addressing sharp minima hindrance in quantum federated learning
• Mitigating vulnerability to adversarial attacks from stable gradients
• Reducing quantum device noise impact on model precision

Innovation

• Incorporates differential privacy for enhanced security
• Introduces noise estimation to mitigate quantum noise
• Uses adaptive noise generation to improve robustness