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

The paper introduces vFedProtoQNAS, a prototype‑guided personalized quantum neural architecture search method for virtual federated learning. It allows each client to independently design and train a device‑specific quantum neural network while avoiding parameter aggregation across structurally different models. Instead, clients share class‑wise latent prototypes, which are refined using global prototypes from the server to serve as federated semantic anchors, leading to a 3.70% accuracy improvement over FedAvg.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• safety