Quantum federated learning personalizes neural networks with prototype sharing
vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning
Artificial Intelligence
Summary
Training quantum neural networks on devices with different capabilities is hard because one network design does not fit all. The authors propose a way where each device searches and trains its own quantum neural network but shares summary information called prototypes instead of network details. This method helps devices collaborate without mixing incompatible network parts. Their approach improves accuracy and helps align how different devices represent data classes.
What this means in practice
- •For quantum device engineers: Design personalized quantum neural networks for devices with different quantum hardware limits by collaborating on class prototypes instead of full model parameters.
- •For federated learning platform developers: Implement federated systems that allow each client to tailor its neural network architecture while maintaining collaborative learning through semantic prototype exchanges.
Authors
Seok Bin Son, Samuel Yen-Chi Chen, Soohyun Park, Joongheon Kim
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.