analiza aiqbench
This research introduces a hybrid quantum-inspired Kolmogorov-Arnold network designed to enhance privacy-preserving federated learning for sensitive ECG data without requiring actual qubits. The study demonstrates that this architecture significantly reduces trainable parameters and communication costs while improving robustness against non-IID data distributions in medical settings. By leveraging algorithmic structures inspired by quantum mechanics, the work offers a practical pathway toward efficient AI models for healthcare applications where raw data sharing is restricted.
Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning
arXiv:2608.13914v1 Announce Type: cross Abstract: Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However, federated ECG classification remains challenging due to limited client-side samples, imbalanced arrhythmia labels, and non-independent and identically distributed (non-IID) data across clients. These constraints require classifiers that are both communication-efficient and robust to cross-client distribution shifts. In this work, we evaluate a hybrid quantum-inspired Kolmogorov-Arnold network (HQKAN) against a multilayer perceptron (MLP) for five-class arrhythmia classification on the MIT-BIH dataset and three-class classification on the INCART dataset under federated averaging (FedAvg). Across multiple client configurations, HQKAN improves most aggregate and minority-class metrics while using 37.35% fewer trainable parameters and reducing communication cost by 24.89% on MIT-BIH; on INCART, it achieves corresponding reductions of 44.81% and 36.41%. These results indicate that HQKAN offers a compact, communication-efficient and robust alternative to the MLP baseline for privacy-aware federated learning on biosignal data.
Abstract:Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However, federated ECG classification remains challenging due to limited client-side samples, imbalanced arrhythmia labels, and non-independent and identically distributed (non-IID) data across clients. These constraints require classifiers that are both communication-efficient and robust to cross-client distribution shifts. In this work, we evaluate a hybrid quantum-inspired Kolmogorov-Arnold network (HQKAN) against a multilayer perceptron (MLP) for five-class arrhythmia classification on the MIT-BIH dataset and three-class classification on the INCART dataset under federated averaging (FedAvg). Across multiple client configurations, HQKAN improves most aggregate and minority-class metrics while using 37.35% fewer trainable parameters and reducing communication cost by 24.89% on MIT-BIH; on INCART, it achieves corresponding reductions of 44.81% and 36.41%. These results indicate that HQKAN offers a compact, communication-efficient and robust alternative to the MLP baseline for privacy-aware federated learning on biosignal data.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Emerging Technologies (cs.ET); Quantum Physics (quant-ph)
arXiv:2608.13914 [cs.LG]
(or arXiv:2608.13914v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.13914 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 207 cuvinte
Subiecte conexe
Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
arXiv · 15 sept. 2026
Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps
arXiv · 7 sept. 2026
Seasonal and Quantum-inspired Models for Neutron Monitor Time Series Forecasting
arXiv · 28 sept. 2026
Domain-Aware Hybrid Quantum Learning via Correlation-Guided Circuit Design for Crime Pattern Analytics
arXiv · 9 sept. 2026