ABSTRACT As an unsupervised feature representation paradigm, Self‐Supervised Learning (SSL) uses the intrinsic structure of data to extract meaningful features without relying on manual annotation. Despite the success of SSL, there are still problems, such as limited model capacity or insufficient representation ability. Quantum SSL has become a promising alternative because it can exploit quantum states to enhance expression ability and learning efficiency. This letter proposes a Quantum SSL with entanglement augmentation method (QSEA). Different from existing Quantum SSLs, QSEA introduces an entanglement‐based sample generation scheme and a fidelity‐driven quantum loss function. Specifically, QSEA constructs augmented samples by entangling an auxiliary qubit with the raw state and applying parameterized unitary transformations. The loss function is defined using quantum fidelity, quantifying similarity between quantum representations and effectively capturing sample relations. Experimental results show that QSEA outperforms existing quantum self‐supervised methods on multiple benchmarks and shows stronger stability in decorrelation noise environments. This framework lays the theoretical and practical foundation for quantum learning systems and advances the development of quantum machine learning in SSL.
ABSTRACT As an unsupervised feature representation paradigm, Self‐Supervised Learning (SSL) uses the intrinsic structure of data to extract meaningful features without relying on manual annotation. Despite the success of SSL, there are still problems, such as limited model capacity or insufficient representation ability. Quantum SSL has become a promising alternative because it can exploit quantum states to enhance expression ability and learning efficiency. This letter proposes a Quantum SSL with entanglement augmentation method (QSEA). Different from existing Quantum SSLs, QSEA introduces an entanglement‐based sample generation scheme and a fidelity‐driven quantum loss function. Specifically, QSEA constructs augmented samples by entangling an auxiliary qubit with the raw state and applying parameterized unitary transformations. The loss function is defined using quantum fidelity, quantifying similarity between quantum representations and effectively capturing sample relations. Experimental results show that QSEA outperforms existing quantum self‐supervised methods on multiple benchmarks and shows stronger stability in decorrelation noise environments. This framework lays the theoretical and practical foundation for quantum learning systems and advances the development of quantum machine learning in SSL.
Self-supervised learning (SSL) has emerged as a novel method for learning representations from inputs without data annotations. A key challenge in SSL is avoiding the collapse of representations, leading to poor predictive models. This research proposes an SSL framework that leverages quantum classifiers to address this issue. We achieve well-stratified, nontrivial representations by embedding data into the Hilbert space via quantum classifiers. The algorithm works by minimizing the Kullback-Leibler (KL) divergence to maximize the agreement of positive pairs and minimize the agreement of negative pairs. We demonstrate the proof-of-concept in image classification tasks using MNIST, KMNIST, and FashionMNIST datasets. Classifiers trained with our framework achieve higher predictive performance than classical classifiers, with a maximum accuracy of 65% on MNIST and more than 70% on KMNIST and FashionMNIST using unseen samples without fine-tuning. The code implementation is available at https://github.com/namhai03/QSSL
This paper explores the potential of quantum computing for unsupervised feature representation learning. Traditional unsupervised methods often rely on manually designed feature extraction algorithms, limiting their applicability to complex datasets. We propose a novel approach leveraging quantum entanglement and quantum gate operations to achieve unsupervised feature extraction directly from raw data. This approach aims to enhance the generalization capability and robustness of machine learning models. The core idea involves constructing a quantum circuit-based model that implicitly maps input data and extracts relevant features through quantum entanglement and gate operations. We present a theoretical framework outlining the methodology and discuss the potential benefits and challenges of this emerging field. The primary goal is to demonstrate that quantum computing offers a fundamentally different paradigm for unsupervised learning, potentially surpassing the limitations of classical approaches. ---
This paper presents a novel approach to quantum machine learning, termed Nonlinear Quantum Self-Adaptive Learning (NQ-SSL). The core principle of NQ-SSL leverages a dynamically adjusted quantum parameter set, achieved through a self-adaptive learning algorithm, to optimize the performance of quantum systems. Traditional quantum learning methods often require extensive manual parameter tuning, limiting the adaptability of quantum algorithms to complex, real-world scenarios. NQ-SSL offers a paradigm shift by allowing the system to learn optimal parameters automatically, leading to enhanced system performance and robust self-adaptation. This work introduces a novel quantum self-adaptation mechanism based on a feedback loop, enhancing the algorithm's ability to navigate and optimize quantum states. We demonstrate the efficacy of NQ-SSL through simulations illustrating improved convergence speed and enhanced performance across a range of quantum benchmark problems.
ABSTRACT Quantum machine learning (QML) aims to leverage the principles of quantum mechanics to speed up the process of solving machine learning problems or improve the quality of solutions. In supervised learning, training samples that are entangled with an auxiliary system were shown to reduce the approximation error of the trained model. However, also the training process is affected by various properties of the supervised learning task, including the model's circuit structure, the used cost function, and noise on the quantum computer. To evaluate the applicability of entanglement in supervised learning, the effect of highly entangled training data on the trainability is investigated in this work. This study shows that for highly expressive models, i.e., models capable of expressing a large number of candidate solutions, the possible improvement of loss function values in constrained neighborhoods during optimization is severely limited when maximally entangled states are used. Furthermore, this finding is experimentally supported by simulating training with Parameterized Quantum Circuits (PQCs). As the expressivity of the PQC increases, this training process becomes more susceptible to loss concentration induced by entangled training data. Lastly, for non‐maximally entangled states, the experiments highlight the fundamental role of entanglement entropy as a predictor for the trainability.
This paper introduces an innovative theoretical framework for quantum-inspired data embeddings, grounded in foundational concepts of quantum mechanics such as superposition and entanglement. This approach aims to advance semi-supervised learning in contexts characterized by limited labeled data by enabling more intricate and expressive embeddings that capture the underlying structure of the data effectively. Grounded in foundational quantum mechanics concepts such as superposition and entanglement, this approach redefines data representation by enabling more intricate and expressive embeddings. Emulating quantum superposition encodes each data point as a probabilistic amalgamation of multiple feature states, facilitating a richer, multidimensional representation of underlying structures and patterns. Additionally, quantum-inspired entanglement mechanisms are harnessed to model intricate dependencies between labeled and unlabeled data, promoting enhanced knowledge transfer and structural inference within the learning paradigm. In contrast to conventional quantum machine learning methodologies that often rely on quantum hardware, this framework is fully realizable within classical computational architectures, thus bypassing the practical limitations of quantum hardware. The versatility of this model is illustrated through its application to critical domains such as medical diagnosis, resource-constrained natural language processing, and financial forecasting—areas where data scarcity impedes the efficacy of traditional models. Experimental evaluations reveal that quantum-inspired embeddings substantially outperform standard approaches, enhancing model resilience and generalization in high-dimensional, low-sample scenarios. This research marks a significant stride in integrating quantum theoretical principles with classical machine learning, broadening the scope of data representation and semi-supervised learning while circumventing the technological barriers of quantum computing infrastructure.
Quantum machine learning (QML) aims to leverage the principles of quantum mechanics to speed up the process of solving machine learning problems or improve the quality of solutions. In supervised learning, training samples that are entangled with an auxiliary system were shown to reduce the approximation error of the trained model. However, also the training process is affected by various properties of the supervised learning task, including the model's circuit structure, the used cost function, and noise on the quantum computer. To evaluate the applicability of entanglement in supervised learning, the effect of highly entangled training data on the trainability is investigated in this work. This study shows that for highly expressive models, i.e., models capable of expressing a large number of candidate solutions, the possible improvement of loss function values in constrained neighborhoods during optimization is severely limited when maximally entangled states are used. Furthermore, this finding is experimentally supported by simulating training with Parameterized Quantum Circuits (PQCs). As the expressivity of the PQC increases, this training process becomes more susceptible to loss concentration induced by entangled training data. Lastly, for non‐maximally entangled states, the experiments highlight the fundamental role of entanglement entropy as a predictor for the trainability.