We present a preliminary proof-of-concept study for using quantum federated learning (QFL) with multi-modal sensor data across distributed platforms. Our approach uses a hybrid quantum-classical model in which each sensing modality is first processed by its own classical encoder. The resulting features are then combined using a learned, entropy-regularized gating mechanism, passed through a variational quantum circuit, and trained using federated averaging. Both the classical model parameters and the quantum circuit parameters are shared and aggregated across clients during training. We evaluate the approach in two separate studies using the AU-AIR aerial UAV dataset and the nuScenes autonomous-driving mini split. Each dataset is federated independently across four clients and represented using four sensing modalities. All results are evaluated on held-out test data across five random seeds and compared with an equivalent classical pipeline in which the quantum circuit is replaced by a classical layer of similar size. The results show that the overall QFL pipeline can be trained successfully. Entropy regularization keeps the modality contributions nearly balanced, and the quantum parameters converge under federated aggregation. On the nuScenes categories represented in the mini split, the quantum model achieves a performance of macro averaged F1-score of of 0.869 and an accuracy of 0.913 . However, the classical baseline performs similarly, with the F1 of 0.853, and the difference is not statistically significant. On AU-AIR, the results are weaker as severe class imbalance and limited circuit capacity reduce held-out accuracy to 0.452. Because the overall results are mixed, the study shows that QFL can be applied to real multi-modal sensing data while also highlighting important limitations. The findings emphasize the need for skew-aware metrics, strong classical baselines, and further work on scalable and reliable quantum federated perception.
We present a preliminary proof-of-concept study for using quantum federated learning (QFL) with multi-modal sensor data across distributed platforms. Our approach uses a hybrid quantum-classical model in which each sensing modality is first processed by its own classical encoder. The resulting features are then combined using a learned, entropy-regularized gating mechanism, passed through a variational quantum circuit, and trained using federated averaging. Both the classical model parameters and the quantum circuit parameters are shared and aggregated across clients during training. We evaluate the approach in two separate studies using the AU-AIR aerial UAV dataset and the nuScenes autonomous-driving mini split. Each dataset is federated independently across four clients and represented using four sensing modalities. All results are evaluated on held-out test data across five random seeds and compared with an equivalent classical pipeline in which the quantum circuit is replaced by a classical layer of similar size. The results show that the overall QFL pipeline can be trained successfully. Entropy regularization keeps the modality contributions nearly balanced, and the quantum parameters converge under federated aggregation. On the nuScenes categories represented in the mini split, the quantum model achieves a performance of macro averaged F1-score of of 0.869 and an accuracy of 0.913 . However, the classical baseline performs similarly, with the F1 of 0.853, and the difference is not statistically significant. On AU-AIR, the results are weaker as severe class imbalance and limited circuit capacity reduce held-out accuracy to 0.452. Because the overall results are mixed, the study shows that QFL can be applied to real multi-modal sensing data while also highlighting important limitations. The findings emphasize the need for skew-aware metrics, strong classical baselines, and further work on scalable and reliable quantum federated perception.
Quantum federated learning (QFL) has been recently introduced to enable a distributed privacy-preserving quantum machine learning (QML) model training across quantum processors (clients). Despite recent research efforts, existing QFL frameworks predominantly focus on unimodal systems, limiting their applicability to real-world tasks that often naturally involve multiple modalities. To fill this significant gap, we present for the first time a novel multimodal approach specifically tailored for the QFL setting with the intermediate fusion using quantum entanglement. Furthermore, to address a major bottleneck in multimodal QFL, where the absence of certain modalities during training can degrade model performance, we introduce a Missing Modality Agnostic (MMA) mechanism that isolates untrained quantum circuits, ensuring stable training without corrupted states. Simulation results demonstrate that the proposed multimodal QFL method with MMA yields an improvement in accuracy of 6.84% in independent and identically distributed (IID) and 7.25% in non-IID data distributions compared to the state-of-the-art methods.
Abstract Currently, data privacy and security are critical in deep learning, especially with biometric data. Federated learning (FL) addresses these concerns, but struggles with security, complexity, and high-dimensional data. Quantum Federated Learning (QFL) overcomes these issues by combining FL with quantum computing, thereby offering greater power and parallelism. In this paper, we propose an innovative QFL approach with a quantum–classical hybrid architecture to address the limitations of classical FL and achieve superior performance in video and image classification. The proposed architecture consists of a classical server and quantum–classical clients. On the client side, after preprocessing the videos and images, a pre-trained model extracts high-level features, which are then classified by a client-specific quantum circuit using a Variational Quantum Circuit (VQC). To maximize the performance of this hybrid system, we jointly optimize the VQC parameters and the weights of the pre-trained model’s final feature-extraction layers. The proposed approach has been extensively evaluated in a simulation environment with random client selection to account for the heterogeneity of real-world systems. Furthermore, we present results obtained from quantum computers using globally optimized VQC parameters. This successful validation on actual quantum hardware underscores the practical applicability of our approach, extending its significance beyond theoretical contributions to next-generation applications such as smart campus security.
In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.
Quantum federated learning (QFL) combines quantum computing and federated learning to enable decentralized model training while maintaining data privacy. QFL can improve computational efficiency and scalability by taking advantage of quantum properties such as superposition and entanglement. However, existing QFL frameworks largely focus on homogeneity among quantum \textcolor{black}{clients, and they do not account} for real-world variances in quantum data distributions, encoding techniques, hardware noise levels, and computational capacity. These differences can create instability during training, slow convergence, and reduce overall model performance. In this paper, we conduct an in-depth examination of heterogeneity in QFL, classifying it into two categories: data or system heterogeneity. Then we investigate the influence of heterogeneity on training convergence and model aggregation. We critically evaluate existing mitigation solutions, highlight their limitations, and give a case study that demonstrates the viability of tackling quantum heterogeneity. Finally, we discuss potential future research areas for constructing robust and scalable heterogeneous QFL frameworks.
Anomaly detection has a significant impact on applications such as video surveillance, medical diagnostics, and industrial monitoring, where anomalies frequently depend on context and anomaly-labeled data are limited. Quantum federated learning (QFL) overcomes these concerns by distributing model training among several quantum clients, consequently eliminating the requirement for centralized quantum storage and processing. However, in real-life quantum networks, clients frequently differ in terms of hardware capabilities, circuit designs, noise levels, and how classical data is encoded or preprocessed into quantum states. These differences create inherent heterogeneity across clients - not just in their data distributions, but also in their quantum processing behaviors. As a result, training a single global model becomes ineffective, especially when clients handle imbalanced or non-identically distributed (non-IID) data. To address this, we propose a new framework called personalized quantum federated learning (PQFL) for anomaly detection. PQFL enhances local model training at quantum clients using parameterized quantum circuits and classical optimizers, while introducing a quantum-centric personalization strategy that adapts each client's model to its own hardware characteristics and data representation. Extensive experiments show that PQFL significantly improves anomaly detection accuracy under diverse and realistic conditions. Compared to state-of-the-art methods, PQFL reduces false errors by up to 23%, and achieves gains of 24.2% in AUROC and 20.5% in AUPR, highlighting its effectiveness and scalability in practical quantum federated settings.
Federated Learning (FL) has become increasingly popular across different sectors, offering a way for clients to work together to train a global model without sharing sensitive data. It involves multiple rounds of communication between the global model and participating clients, which introduces several challenges like high communication costs, heterogeneous client data, prolonged processing times, and increased vulnerability to privacy threats. In recent years, the convergence of federated learning and parameterized quantum circuits has sparked significant research interest, with promising implications for fields such as healthcare and finance. By enabling decentralized training of quantum models, it allows clients or institutions to collaboratively enhance model performance and outcomes while preserving data privacy. Recognizing that Fisher information can quantify the amount of information that a quantum state carries under parameter changes, thereby providing insight into its geometric and statistical properties. We intend to leverage this property to address the aforementioned challenges. In this work, we propose a Quantum Federated Learning (QFL) algorithm that makes use of the Fisher information computed on local client models, with data distributed across heterogeneous partitions. This approach identifies the critical parameters that significantly influence the quantum model's performance, ensuring they are preserved during the aggregation process. Our research assessed the effectiveness and feasibility of QFL by comparing its performance against other variants, and exploring the benefits of incorporating Fisher information in QFL settings. Experimental results on ADNI and MNIST datasets demonstrate the effectiveness of our approach in achieving better performance and robustness against the quantum federated averaging method.