SimQFL: A Quantum Federated Learning Simulator with Real-Time Visualization

TL;DR

This paper tackles the lack of practical tooling for quantum federated learning by introducing SimQFL, a lightweight simulator with real-time visualization and user-data support. It integrates amplitude-encoded data, variational quantum circuits, and federated aggregation to enable end-to-end QFL experiments without real quantum devices. Empirical results on MNIST, FashionMNIST, and CIFAR-100 show that QFL can exceed classical FL in accuracy and convergence speed, and the work maps out how qubit count, circuit depth, and client participation shape learning dynamics. The standalone executable and interactive UI make SimQFL a reusable platform for prototyping, benchmarking, and teaching QFL concepts in realistic distributed settings.

Abstract

Quantum federated learning (QFL) is an emerging field that has the potential to revolutionize computation by taking advantage of quantum physics concepts in a distributed machine learning (ML) environment. However, the majority of available quantum simulators are primarily built for general quantum circuit simulation and do not include integrated support for machine learning tasks such as training, evaluation, and iterative optimization. Furthermore, designing and assessing quantum learning algorithms is still a difficult and resource-intensive task. Real-time updates are essential for observing model convergence, debugging quantum circuits, and making conscious choices during training with the use of limited resources. Furthermore, most current simulators fail to support the integration of user-specific data for training purposes, undermining the main purpose of using a simulator. In this study, we introduce SimQFL, a customized simulator that simplifies and accelerates QFL experiments in quantum network applications. SimQFL supports real-time, epoch-wise output development and visualization, allowing researchers to monitor the process of learning across each training round. Furthermore, SimQFL offers an intuitive and visually appealing interface that facilitates ease of use and seamless execution. Users can customize key variables such as the number of epochs, learning rates, number of clients, and quantum hyperparameters such as qubits and quantum layers, making the simulator suitable for various QFL applications. The system gives immediate feedback following each epoch by showing intermediate outcomes and dynamically illustrating learning curves. SimQFL is a practical and interactive platform enabling academics and developers to prototype, analyze, and tune quantum neural networks with greater transparency and control in distributed quantum networks.

Figures (4)

• Figure 1: Overview of the QFL architecture with $N$ quantum clients and a classical server within the QFL framework. Each client encodes conventional input into quantum states and is trained using local Quantum Machine Learning (QML) models. The server aggregates the parameters of the local models and updates the global model parameters for the next round.
• Figure 2: This is a simulator visualization that shows the overall structure of our simulator and the overview of the SimQFL simulator's user interface. Key navigation pathways between the various system components are depicted in the screenshots: (a) default home screen; (b) simulation with standard datasets; (c) simulation with user datasets; (d) simulation with uploaded datasets; (e) hyper-parameter settings; (f) graphical outputs; and (g) saving results.
• Figure 3: System diagram of quantum client's communication on the proposed QFL Simulator. Components include local data, an encoder, quantum-encoded data, a quantum model for every Quantum Client, and global aggregation on a classical server.
• Figure 4: Performance comparison between FL with quantum model (QFL), and FL with classical model (classical FL) approaches. We use MNIST, Fashion-MNIST, and CIFAR-100 datasets for comparison.