Quantum Federated Learning: Architectural Elements and Future Directions

TL;DR

The work addresses the limitations of classical federated learning, including high compute demands, privacy risks, and communication overhead, by proposing Quantum Federated Learning (QFL) as a hybrid quantum‑classical paradigm. It presents an architectural blueprint, a four‑axis taxonomy (quantum architecture, data processing, topology, and security), and multiple domain applications where QFL can improve efficiency and privacy. Two case studies illustrate end‑to‑end QFL implementations: a privacy‑preserving fraud detection framework using QLSTM and a satellite‑oriented sat‑QFL design with secure quantum communications and adaptive scheduling. The discussion highlights practical challenges—hardware realism, adversarial resilience, secure quantum communication deployment, and the potential of quantum split learning—to guide future research and real‑world deployment of QFL systems.

Abstract

Federated learning (FL) focuses on collaborative model training without the need to move the private data silos to a central server. Despite its several benefits, the classical FL is plagued with several limitations, such as high computational power required for model training(which is critical for low-resource clients), privacy risks, large update traffic, and non-IID heterogeneity. This chapter surveys a hybrid paradigm - Quantum Federated Learning (QFL), which introduces quantum computation, that addresses multiple challenges of classical FL and offers rapid computing capability while keeping the classical orchestration intact. Firstly, we motivate QFL with a concrete presentation on pain points of classical FL, followed by a discussion on a general architecture of QFL frameworks specifying the roles of client and server, communication primitives and the quantum model placement. We classify the existing QFL systems based on four criteria - quantum architecture (pure QFL, hybrid QFL), data processing method (quantum data encoding, quantum feature mapping, and quantum feature selection & dimensionality reduction), network topology (centralized, hierarchial, decentralized), and quantum security mechanisms (quantum key distribution, quantum homomorphic encryption, quantum differential privacy, blind quantum computing). We then describe applications of QFL in healthcare, vehicular networks, wireless networks, and network security, clearly highlighting where QFL improves communication efficiency, security, and performance compared to classical FL. We close with multiple challenges and future works in QFL, including extension of QFL beyond classification tasks, adversarial attacks, realistic hardware deployment, quantum communication protocols deployment, aggregation of different quantum models, and quantum split learning as an alternative to QFL.

Figures (11)

• Figure 1: Centralized QFL architecture.
• Figure 2: Classification framework for QFL systems based on architecture, data processing, topology, and security mechanism dimensions.
• Figure 5: Quantum Homomorphic Encryption security mechanism in a QFL framework
• Figure 6: Training workflow of our framework demonstrating local quantum-enhanced computations, federated aggregation, and secure update exchanges
• Figure 7: QLSTM model demonstrating a 3-sequence architecture with output taken only at the last cell. Each cell processes the input at that time step (t) as $\mathbf{X}_t$ and generates a hidden state $\mathbf{h}_t$, and the output $\mathbf{Y}_{t}$.