Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Sakarya University Journal of Computer and Information Sciences

Quantum-Inspired Data Embedding for Unlabeled Data in Sparse Environments: A Theoretical Framework for Improved Semi-Supervised Learning without Hardware Dependence

Shawn Ray

Published Dec 31, 2024• 1 citation
Publisher

Abstract

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.

DOI
10.35377/saucis...1564497

Related papers

Supervised Learning with Quantum Hamiltonian Embeddings

Riccardo Molteni, Minjun Jeon, Paolo Braccia +8 more

Machine learning is widely regarded as a promising application in which quantum computing could offer a computational advantage. However, general quantum machine learning models with provable guarantees on performance, trainability, and efficient inference remain limited. In this work, we introduce quantum Hamiltonian embeddings, a supervised learning framework in which a classical training dataset is encoded into a single effective, parameterized Hamiltonian. Training optimizes the parameters of this data-dependent Hamiltonian, whose approximate ground state defines the classification rule. Once the ground state has been approximated using a quantum algorithm, inference can be performed either classically using a classical representation of the learned state, or with a quantum representation of the state. We establish efficient methods for gradient estimation and prove favorable generalization guarantees. Furthermore, under standard cryptographic assumptions, we show that Hamiltonian embeddings can realize hypothesis functions beyond the reach of efficient classical algorithms. We then demonstrate the framework at scale on IBM Heron processors using a standard benchmark dataset. Together, these results establish Hamiltonian embeddings as a new framework for quantum machine learning, combining theoretical guarantees with a path for experimental investigations at scale on quantum hardware.

quant-pharXiv:2610.26833•Oct 20, 2026•0 citations

Quantum-Inspired Feature Embeddings for Semi-Supervised Learning in Sparse Label Regimes: A Variational Framework with Classical Simulation Guarantees

Zhang Wei

Semi-supervised learning (SSL) has emerged as a critical paradigm for leveraging abundant unlabeled data alongside scarce labeled samples, yet classical approaches often struggle in sparse label regimes where the ratio of labeled to unlabeled data is extremely low. Meanwhile, quantum machine learning (QML) has demonstrated that quantum feature spaces can induce rich kernel structures with provable representational advantages, but these methods typically require quantum hardware that remains inaccessible for practical deployment. In this work, we propose a quantum-inspired semi-supervised learning framework that harnesses the geometric properties of quantum Hilbert space embeddings while remaining entirely classical and hardware-independent. Our approach, which we term Quantum-Inspired SemiSupervised Learning (QISSL), constructs feature maps that mimic the action of quantum encoding circuits via classically simulable kernel functions derived from randomized trigonometric expansions. We provide rigorous theoretical analysis establishing: (1) a bounded approximation guarantee between our classical embeddings and their quantum counterparts; (2) a generalization bound for QISSL under low-label regimes via Rademacher complexity analysis; and (3) a convergence proof for the alternating optimization procedure that jointly trains the embedding and classifier modules. Extensive experiments on benchmark datasets demonstrate that QISSL achieves state-of-the-art performance in extreme low-label settings (0.1%–1% labeled data), outperforming strong baselines including FixMatch, MixMatch, and FlexMatch by margins of 2–7% in accuracy. Our results suggest that the inductive biases of quantum feature spaces—when properly classically approximated—offer a powerful and practical tool for semi-supervised learning without quantum hardware.

•Apr 24, 2026•0 citations

A Unified Advanced Framework for Sparse Data Modeling in Quantum-Enhanced Artificial Intelligence

Murali Krishna Pasupuleti

Abstract: Sparse and high-dimensional data present persistent challenges in artificial intelligence (AI), particularly in maintaining generalizability, interpretability, and computational efficiency. This study proposes a unified advanced framework that integrates tensor algebra, number theory, topology, and analytic geometry to address the limitations of traditional machine learning models when handling sparse data. The methodology leverages high-order tensor representations for compact and expressive encoding of multi-dimensional information, modular arithmetic for robust and secure feature embedding, and persistent homology to capture topological invariants within data distributions. Additionally, geometric learning principles based on Riemannian manifolds are incorporated to guide optimization processes through curvature-aware gradient flows. The proposed framework is further enhanced by quantum computational principles, where tensor networks and entangled state representations are simulated for efficient processing. Experimental evaluation on classical and quantum datasets demonstrates superior performance in terms of accuracy, F1 score, and convergence rate when compared to baseline and modular AI architectures. The results validate that the integration of mathematical rigor and quantum principles can offer scalable, interpretable, and resilient solutions for sparse data modeling. This framework not only contributes to the theoretical foundation of AI and quantum learning but also provides practical implications for applications in cryptography, biomedical analysis, and high-dimensional signal processing. Keywords Sparse data modeling, tensor algebra, quantum machine learning, topological data analysis, modular arithmetic, Riemannian geometry, tensor networks, persistent homology, quantum-enhanced AI, high-dimensional data

International Journal of Academic and Industrial Research Innovations(IJAIRI)•Jul 23, 2025•0 citations

基于张量信息的量子机器学习模型

Jincheng Zhang

This paper introduces a novel quantum machine learning model leveraging the power of tensor information. Traditional machine learning models often struggle with complex, non-linear relationships, hindering their ability to generalize effectively. We propose a quantum-enhanced learning framework that encodes data into quantum tensors, utilizing quantum entanglement and superposition to accelerate training and improve model robustness. This work addresses the limitations of classical machine learning by harnessing the unique properties of quantum systems. The core mechanism involves encoding data into quantum tensors, employing quantum machine learning algorithms, and exploiting the inherent properties of quantum entanglement and superposition to enhance learning efficiency and generalization. This research explores the potential of quantum computing to significantly advance the field of machine learning, particularly in scenarios requiring handling intricate data dependencies.

•Sep 3, 2026•0 citations

Quantum-Inspired Machine Learning: A New Paradigm for Complex Data Processing

Yaareb T. Ahmed AL-Tamimi

This study aims to evaluate the effectiveness of quantum-inspired machine learning (QIML) techniques when applied to high-dimensional data processing problems. Instead of relying on quantum hardware, QIML uses concepts such as amplitude encoding and tensor networks to improve the efficiency of traditional models. We compared the performance of QIML models with traditional machine learning models on three real-world datasets in the fields of finance, medical diagnosis, and natural language processing. The study used metrics of accuracy, training speed, and generalization properties for comparison. Our results show that hybrid QIML models achieve up to a 10% improvement in accuracy and a 40% improvement in training speed compared to traditional models. We also discuss current limitations in scalability and computational cost and suggest future research directions for developing QIML as an effective tool for processing complex data.

Iraqi journal for applied science.•Sep 30, 2025•0 citations

Quantum Machine Learning via Contrastive Training

Liudmila A. Zhukas, Vivian Ni Zhang, Qiang Miao +5 more

Quantum machine learning (QML) has attracted growing interest with the rapid parallel advances in large-scale classical machine learning and quantum technologies. Similar to classical machine learning, QML models also face challenges arising from the scarcity of labeled data, particularly as their scale and complexity increase. Here, we introduce self-supervised pretraining of quantum representations that reduces reliance on labeled data by learning invariances from unlabeled examples. We implement this paradigm on a programmable trapped-ion quantum computer, encoding images as quantum states. In situ contrastive pretraining on hardware yields a representation that, when fine-tuned, classifies image families with higher mean test accuracy and lower run-to-run variability than models trained from random initialization. Performance improvement is especially significant in regimes with limited labeled training data. We show that the learned invariances generalize beyond the pretraining image samples. Unlike prior work, our pipeline derives similarity from measured quantum overlaps and executes all training and classification stages on hardware. These results establish a label-efficient route to quantum representation learning, with direct relevance to quantum-native datasets and a clear path to larger classical inputs.

cs.LGCross-listedarXiv:2511.13497•Nov 18, 2025•1 citation
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.
Machine learning is widely regarded as a promising application in which quantum computing could offer a computational advantage. However, general quantum machine learning models with provable guarantees on performance, trainability, and efficient inference remain limited. In this work, we introduce quantum Hamiltonian embeddings, a supervised learning framework in which a classical training dataset is encoded into a single effective, parameterized Hamiltonian. Training optimizes the parameters of this data-dependent Hamiltonian, whose approximate ground state defines the classification rule. Once the ground state has been approximated using a quantum algorithm, inference can be performed either classically using a classical representation of the learned state, or with a quantum representation of the state. We establish efficient methods for gradient estimation and prove favorable generalization guarantees. Furthermore, under standard cryptographic assumptions, we show that Hamiltonian embeddings can realize hypothesis functions beyond the reach of efficient classical algorithms. We then demonstrate the framework at scale on IBM Heron processors using a standard benchmark dataset. Together, these results establish Hamiltonian embeddings as a new framework for quantum machine learning, combining theoretical guarantees with a path for experimental investigations at scale on quantum hardware.
Semi-supervised learning (SSL) has emerged as a critical paradigm for leveraging abundant unlabeled data alongside scarce labeled samples, yet classical approaches often struggle in sparse label regimes where the ratio of labeled to unlabeled data is extremely low. Meanwhile, quantum machine learning (QML) has demonstrated that quantum feature spaces can induce rich kernel structures with provable representational advantages, but these methods typically require quantum hardware that remains inaccessible for practical deployment. In this work, we propose a quantum-inspired semi-supervised learning framework that harnesses the geometric properties of quantum Hilbert space embeddings while remaining entirely classical and hardware-independent. Our approach, which we term Quantum-Inspired SemiSupervised Learning (QISSL), constructs feature maps that mimic the action of quantum encoding circuits via classically simulable kernel functions derived from randomized trigonometric expansions. We provide rigorous theoretical analysis establishing: (1) a bounded approximation guarantee between our classical embeddings and their quantum counterparts; (2) a generalization bound for QISSL under low-label regimes via Rademacher complexity analysis; and (3) a convergence proof for the alternating optimization procedure that jointly trains the embedding and classifier modules. Extensive experiments on benchmark datasets demonstrate that QISSL achieves state-of-the-art performance in extreme low-label settings (0.1%–1% labeled data), outperforming strong baselines including FixMatch, MixMatch, and FlexMatch by margins of 2–7% in accuracy. Our results suggest that the inductive biases of quantum feature spaces—when properly classically approximated—offer a powerful and practical tool for semi-supervised learning without quantum hardware.
Abstract: Sparse and high-dimensional data present persistent challenges in artificial intelligence (AI), particularly in maintaining generalizability, interpretability, and computational efficiency. This study proposes a unified advanced framework that integrates tensor algebra, number theory, topology, and analytic geometry to address the limitations of traditional machine learning models when handling sparse data. The methodology leverages high-order tensor representations for compact and expressive encoding of multi-dimensional information, modular arithmetic for robust and secure feature embedding, and persistent homology to capture topological invariants within data distributions. Additionally, geometric learning principles based on Riemannian manifolds are incorporated to guide optimization processes through curvature-aware gradient flows. The proposed framework is further enhanced by quantum computational principles, where tensor networks and entangled state representations are simulated for efficient processing. Experimental evaluation on classical and quantum datasets demonstrates superior performance in terms of accuracy, F1 score, and convergence rate when compared to baseline and modular AI architectures. The results validate that the integration of mathematical rigor and quantum principles can offer scalable, interpretable, and resilient solutions for sparse data modeling. This framework not only contributes to the theoretical foundation of AI and quantum learning but also provides practical implications for applications in cryptography, biomedical analysis, and high-dimensional signal processing. Keywords Sparse data modeling, tensor algebra, quantum machine learning, topological data analysis, modular arithmetic, Riemannian geometry, tensor networks, persistent homology, quantum-enhanced AI, high-dimensional data
This paper introduces a novel quantum machine learning model leveraging the power of tensor information. Traditional machine learning models often struggle with complex, non-linear relationships, hindering their ability to generalize effectively. We propose a quantum-enhanced learning framework that encodes data into quantum tensors, utilizing quantum entanglement and superposition to accelerate training and improve model robustness. This work addresses the limitations of classical machine learning by harnessing the unique properties of quantum systems. The core mechanism involves encoding data into quantum tensors, employing quantum machine learning algorithms, and exploiting the inherent properties of quantum entanglement and superposition to enhance learning efficiency and generalization. This research explores the potential of quantum computing to significantly advance the field of machine learning, particularly in scenarios requiring handling intricate data dependencies.
This study aims to evaluate the effectiveness of quantum-inspired machine learning (QIML) techniques when applied to high-dimensional data processing problems. Instead of relying on quantum hardware, QIML uses concepts such as amplitude encoding and tensor networks to improve the efficiency of traditional models. We compared the performance of QIML models with traditional machine learning models on three real-world datasets in the fields of finance, medical diagnosis, and natural language processing. The study used metrics of accuracy, training speed, and generalization properties for comparison. Our results show that hybrid QIML models achieve up to a 10% improvement in accuracy and a 40% improvement in training speed compared to traditional models. We also discuss current limitations in scalability and computational cost and suggest future research directions for developing QIML as an effective tool for processing complex data.
Quantum machine learning (QML) has attracted growing interest with the rapid parallel advances in large-scale classical machine learning and quantum technologies. Similar to classical machine learning, QML models also face challenges arising from the scarcity of labeled data, particularly as their scale and complexity increase. Here, we introduce self-supervised pretraining of quantum representations that reduces reliance on labeled data by learning invariances from unlabeled examples. We implement this paradigm on a programmable trapped-ion quantum computer, encoding images as quantum states. In situ contrastive pretraining on hardware yields a representation that, when fine-tuned, classifies image families with higher mean test accuracy and lower run-to-run variability than models trained from random initialization. Performance improvement is especially significant in regimes with limited labeled training data. We show that the learned invariances generalize beyond the pretraining image samples. Unlike prior work, our pipeline derives similarity from measured quantum overlaps and executes all training and classification stages on hardware. These results establish a label-efficient route to quantum representation learning, with direct relevance to quantum-native datasets and a clear path to larger classical inputs.