Quantum federated learning (QFL) lets multiple quantum clients collaboratively train quantum neural networks (QNNs) without sharing private local data. However, existing QFL methods commonly assume that all clients use the same ansatz, overlooking how heterogeneous client data affects ansatz suitability. Under class-imbalanced non-IID data, different clients may favor different ansatz structures, so a fixed ansatz can lead to unstable and unfair performance across clients. In this paper, we propose PAS-QFL, a Personalized Ansatz Selection framework for QFL under client data heterogeneity. Rather than treating the ansatz as a monolithic structure, PAS-QFL decomposes each client QNN into a globally shared ansatz and a client-specific private ansatz, and personalizes the structure of the private ansatz rather than only its parameters. The shared ansatz is placed first and selected by a stability-aware cross-client criterion so that its parameters can be reliably aggregated, while the private ansatz serves as a personalized decision head, selected per client by local Macro-F1 to adapt the shared representation to its local data. During training, each client updates both its shared and private parameters locally but uploads only the shared parameters, so federated aggregation stays well-defined while each client keeps its own private structure. PAS-QFL uses Macro-F1 as the primary selection metric to avoid misleading accuracy under class imbalance. Experiments on heterogeneous QFL tasks show that PAS-QFL improves average Macro-F1 over the existing fixed-ansatz QFL baselines, demonstrating the value of personalizing the ansatz structure for practical QFL.
Figures & tables
Fig. 1: Overview of PAS-QFL. Each client QNN is decomposed into a globally shared ansatz S(θi) , and a client-specific private ansatz Pi(ϕi) that follows it as a personalized decision head. The shared ansatz is selected for stable cross-client performance, while each private ansatz is selected per client by local profiling. During federated training, every client updates both its private parameters ϕi and its shared parameters θi on local data, but uploads only θi to the central server, which aggregates them into θˉ and broadcasts θˉ back for the next round. The private ansatz structure and its parameters remain local and are never shared.
Fig. 2: Candidate ansatz pool. PAS-QFL considers multiple ansatz structures with different entanglement patterns.
Fig. 3: Local ansatz profiling under client data heterogeneity. The client-wise view summarizes the validation Macro-F1 distribution of different ansatzes on each client, showing client-dependent sensitivity to ansatz choice. The ansatz-wise view summarizes the validation Macro-F1 distribution of each ansatz across clients, showing different levels of their cross-client stability.
Fig. 4: Overall performance under noiseless simulation.
Fig. 5: Overall performance under noisy simulation.
Fig. 6: Effect of personalized private ansatz selection on the FM-2 task with 5 clients. Fixed-private baselines use the same private ansatz structure for all clients, while PAS-QFL selects client-specific private ansatzes through local profiling.
Fig. 7: Effect of shared ansatz selection on the FM-2 task with 5 clients. The personalized private ansatzes are fixed according to PAS-QFL, while the shared ansatz is varied across the candidate ansatz pool.