Federated learning is essential for decentralized, privacy-preserving model training in the data-driven era. Quantum-enhanced federated learning leverages quantum resources to address privacy and scalability challenges, offering security and efficiency advantages beyond classical methods. However, practical and scalable frameworks addressing privacy concerns in the quantum computing era remain undeveloped. Here, we propose a practical quantum federated learning framework on quantum networks, utilizing distributed quantum secret keys to protect local model updates and enable secure aggregation with information-theoretic security. We experimentally validate our framework on a 4-client quantum network with a scalable structure. Extensive numerical experiments on both quantum and classical datasets show that adding a quantum client significantly enhances the trained global model's ability to classify multipartite entangled and non-stabilizer quantum datasets. Simulations further demonstrate scalability to 200 clients with classical models trained on the MNIST dataset, reducing communication costs by $75\%$ through advanced model compression techniques and achieving rapid training convergence. Our work provides critical insights for building scalable, efficient, and quantum-secure machine learning systems for the coming quantum internet era.

With the contemporary digital technology approaching, deep neural networks are emerging as the foundational algorithm of the artificial intelligence boom. Whereas, the evolving social demands have been emphasizing the necessity of novel methodologies to substitute traditional neural networks. Concurrently, the advent of the post-Moore era has spurred the development of quantum-inspired neural networks with outstanding potentials at certain circumstances. Nonetheless, a definitive evaluating system with detailed metrics is tremendously vital and indispensable owing to the vague indicators in comparison between the novel and traditional deep learning models at present. Hence, to improve and evaluate the performances of the novel neural networks more comprehensively in complex and unpredictable environments, we propose two hybrid quantum-inspired neural networks which are rooted in residual and dense connections respectively for pattern recognitions with completeness representation theory for model assessment. Comparative analyses against pure classical models with detailed frameworks reveal that our hybrid models with lower parameter complexity not only match the generalization power of pure classical models, but also outperform them notably in resistance to parameter attacks with various asymmetric noises. Moreover, our hybrid models indicate unique superiority to prevent gradient explosion problems through theoretical argumentation. Eventually, We elaborate on the application scenarios where our hybrid models are applicable and efficient, which paves the way for their industrialization and commercialization.

Neural networks have achieved impressive breakthroughs in both industry and academia. How to effectively develop neural networks on quantum computing devices is a challenging open problem. Here, we propose a new quantum neural network model for quantum neural computing using (classically-controlled) single-qubit operations and measurements on real-world quantum systems with naturally occurring environment-induced decoherence, which greatly reduces the difficulties of physical implementations. Our model circumvents the problem that the state-space size grows exponentially with the number of neurons, thereby greatly reducing memory requirements and allowing for fast optimization with traditional optimization algorithms. We benchmark our model for handwritten digit recognition and other nonlinear classification tasks. The results show that our model has an amazing nonlinear classification ability and robustness to noise. Furthermore, our model allows quantum computing to be applied in a wider context and inspires the earlier development of a quantum neural computer than standard quantum computers.

A new paradigm of quantum computing, namely, soft quantum computing, is proposed for nonclassical computation using real world quantum systems with naturally occurring environment-induced decoherence and dissipation. As a specific example of soft quantum computing, we suggest a quantum neural network, where the neurons connect pairwise via the "controlled Kraus operations", hoping to pave an easier and more realistic way to quantum artificial intelligence and even to better understanding certain functioning of the human brain. Our quantum neuron model mimics as much as possible the realistic neurons and meanwhile, uses quantum laws for processing information. The quantum features of the noisy neural network are uncovered by the presence of quantum discord and by non-commutability of quantum operations. We believe that our model puts quantum computing into a wider context and inspires the hope to build a soft quantum computer much earlier than the standard one.