vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning

2026-10-01

AI Summary

This study addresses the challenges in quantum federated learning where device heterogeneity renders single-architecture approaches inadequate and cross-architecture parameter aggregation causes semantic inconsistencies. To overcome these limitations, this work proposes a class-prototype-based virtual federated learning framework. Each client independently constructs a personalized network via quantum neural architecture search, while collaborative training and knowledge alignment are achieved by sharing class prototypes instead of model parameters. This approach introduces a pioneering virtual federation mechanism that entirely circumvents heterogeneous parameter aggregation, simultaneously preserving semantic consistency and privacy protection. Experimental results demonstrate that the proposed method improves accuracy by 3.70% over FedAvg, significantly enhances inter-class representation consistency, and effectively accommodates resource-constrained quantum devices.

Abstract

Quantum federated learning (QFL) has emerged as a promising approach for collaboratively training compact quantum neural networks (QNNs) over distributed private data on resource-constrained devices. However, differences in device capabilities make a single shared QNN architecture unsuitable for all clients. While personalized quantum neural architecture search (QNAS) allows each client to select a device-specific QNN, averaging parameters across structurally different QNN architectures mixes semantically inconsistent circuit operations. To address this, prototype-guided personalized QNAS for virtual FL (vFedProtoQNAS) is proposed, where model parameters are never aggregated across clients and federated collaboration is achieved through class-wise prototype sharing. Each client independently searches and trains a client-specific QNN, computes class-wise local prototypes from latent representations, and refines them using global prototypes from the server as federated semantic anchors. Experiments demonstrate that vFedProtoQNAS improves accuracy by 3.70\% over FedAvg and enhances class-consistent representation alignment.

Problem

• Quantum Federated Learning
• Personalized Quantum Neural Architecture Search
• Heterogeneous Devices
• Parameter Aggregation
• Semantic Inconsistency

Innovation

• Quantum Federated Learning
• Neural Architecture Search
• Prototype-Guided Learning
• Personalized QNN
• Virtual Federated Learning