AQMLator – an auto quantum machine-learning e-platform

• Autorzy: Rybotycki Tomasz , Gawron Piotr

Identyfikatory

DOI

10.7494/csci.2025.26.SI.7063

• Języki publikacji: EN

Abstrakty

EN

The successful implementation of a machine-learning (ML) model requires three main components: a training data set, a suitable model architecture, and a suitable training procedure. Given the data set and task, finding an appropriate model might be challenging. AutoML, a branch of ML, focuses on an automatic architecture search – a meta method that aims to remove the need for human interaction with the ML system-design process. The success of ML and the development of quantum computing (QC) in recent years has led to the birth of a new fascinating field called quantum machine learning (QML), which incorporates quantum computers into ML models (among other things). In this paper, we present AQMLator, an auto quantum machine-learning platform that aimsto automatically propose and train the quantum layers of an ML model with minimal input from the user. In this way, data scientists can bypass the entry barrier for QC and use QML. AQMLator uses standard ML libraries, making it easy to introduce into existing ML pipelines.

Słowa kluczowe

EN

auto machine learning; quantum computing; quantum machine learning

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2025
• Tom: T. 26 (SI)
• Strony: 29--43
• Opis fizyczny: Bibliogr. 32 poz., rys., tab., wykr.

Twórcy

autor

Rybotycki Tomasz

• Systems Research Institute of the Polish Academy of Sciences, Newelska 6, 01-447 Warsaw, Poland
• Nicolaus Copernicus Astronomical Center of the Polish Academy of Sciences, Bartycka 18, 00-716 Warsaw, Poland
• Center of Excellence in Artificial Intelligence of AGH University, al. Mickiewicza 30, 30-059Krakow, Poland

autor

Gawron Piotr

• Nicolaus Copernicus Astronomical Center of the Polish Academy of Sciences, Bartycka 18, 00-716 Warsaw, Poland
• Center of Excellence in Artificial Intelligence of AGH University, al. Mickiewicza 30, 30-059 Krakow, Poland

Bibliografia

• [1] Akiba T., Sano S., Yanase T., Ohta T., Koyama M.: Optuna: A Next-generation Hyperparameter Optimization Framework, 2019. https://arxiv.org/abs/1907.10902.
• [2] Altares-López S., García-Ripoll J.J., Ribeiro A.: AutoQML: Quantum Inspired Kernels by Using Genetic Algorithms for Grayscale Images [Source Code], https://codeocean.com/capsule/5670396/tree, 2023. doi: 10.24433/CO.3955535.v1.
• [3] Altares-López S., García-Ripoll J.J., Ribeiro A.: AutoQML: Automatic genera-tion and training of robust quantum-inspired classifiers by using evolutionary algorithms on grayscale images, Expert Systems with Applications, vol. 244, 122984,2024. doi: 10.1016/j.eswa.2023.122984.
• [4] Arute F., Arya K., Babbush R., Bacon D., Bardin J.C., Barends R., Biswas R., et al.: Quantum supremacy using a programmable superconducting processor, Nature, vol. 574(7779), pp. 505–510, 2019.
• [5] AutoQML Team: AutoQML Repository, https://github.com/AutoQML, 2023. Accessed: 2024-09-18.
• [6] Benedetti M., Lloyd E., Sack S., Fiorentini M.: Parameterized quantum circuitsas machine learning models, Quantum Science and Technology, vol. 4(4), 043001, 2019. doi: 10.1088/2058-9565/ab4eb5.
• [7] Biamonte J., Wittek P., Pancotti N., Rebentrost P., Wiebe N., Lloyd S.: Quantum machine learning, Nature, vol. 549(7671), pp. 195–202, 2017.
• [8] Bowles J., Ahmed S., Schuld M.: Better than classical? The subtle art of benchmarking quantum machine learning models, 2024. https://arxiv.org/abs/2403.07059.
• [9] Cerezo M., Verdon G., Huang H.Y., Cincio L., Coles P.J.: Challenges and opportunities in quantum machine learning, Nature Computational Science, vol. 2, pp. 567–576, 2022. doi: 10.1038/s43588-022-00311-3.
• [10] Feral Qubits: QBM4EO: Supervised quantum machine learning system for Earthland cover understanding., https://feralqubits.github.io/qbm4eo-lp/. Accessed:2024-09-18.
• [11] Gentile A., Flynn B., Knauer S., Wiebe N., Paesani S., Granade C.E., Rarity J.G.,et al.: Learning models of quantum systems from experiments, Nature Physics, vol. 17, pp. 837–843, 2021. doi: 10.1038/s41567-021-01201-7.
• [12] Guerra E., Wilhelmi F., Miozzo M., Dini P.: The Cost of Training Machine Learning Models Over Distributed Data Sources, IEEE Open Journal of the Communications Society, vol. 4, pp. 1111–1126, 2023. doi: 10.1109/OJCOMS.2023.3274394.
• [13] Herbst S., Maio V.D., Brandic I.: On Optimizing Hyperparameters for Quantum Neural Networks, 2024. https://arxiv.org/abs/2403.18579.
• [14] Hutter F., Kotthoff L., Vanschoren J. (eds.): Automated Machine Learning, Springer International Publishing, 2019.
• [15] Hutter F., Kotthoff L., Vanschoren J. (eds.): Automated Machine Learning: Methods, Systems, Challenges, Springer, Cham, 2019. doi: 10.1007/978-3-030-05318-5.
• [16] Klau D., Krause H., Kreplin D., Roth M., Tutschku C., Zöller M.: Auto-QML – A Framework for Automated Quantum Machine Learning, Technical Report, 2023. https://www.digital.iao.fraunhofer.de/content/dam/iao/ikt/de/documents/AutoQML_Framework.pdf.
• [17] Klau D., Zöller M., Tutschku C.: Bringing Quantum Algorithms to Automated Machine Learning: A Systematic Review of AutoML Frameworks Regarding Extensibility for QML Algorithms, 2023. https://arxiv.org/abs/2310.04238.
• [18] Koike-Akino T., Wang P., Wang Y.: AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications, 2022. https://arxiv.org/abs/2205.09115.
• [19] Kundu A.: Reinforcement learning-assisted quantum architecture search for variational quantum algorithms, 2024. https://arxiv.org/abs/2402.13754.
• [20] Kundu A., Sarkar A., Sadhu A.: KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search, 2024. https://arxiv.org/abs/2406.17630.
• [21] Lusnig L., Sagingalieva A., Surmach M., Protasevich T., Michiu O., McLough-lin J., Mansell C.,et al.: Hybrid Quantum Image Classification and Federated Learning for Hepatic Steatosis Diagnosis, Diagnostics, vol. 14(5), 2024.doi: 10.3390/diagnostics14050558.
• [22] Martyniuk D., Jung J., Paschke A.: Quantum Architecture Search: A Survey, 2024. https://arxiv.org/abs/2406.06210.
• [23] Moussa C., Patel Y.J., Dunjko V., Bäck T., van Rijn J.N.: Hyperparameter importance and optimization of quantum neural networks across small datasets, Machine Learning, vol. 113, pp. 1941–1966, 2024. doi: 10.1007/s10994-023-06389-8.
• [24] Moussa C., van Rijn J.N., Bäck T., Dunjko V.: Hyper parameter Importance of Quantum Neural Networks Across Small Datasets. In: P. Pascal, D. Ienco (eds.), Discovery Science, Lecture Notes in Computer Science, vol. 13601, pp. 32–46, Springer, Cham, 2022. doi: 10.1007/978-3-031-18840-4_3.
• [25] Ostaszewski M., Trenkwalder L.M., Masarczyk W., Scerri E., Dunjko V.: Reinforcement learning for optimization of variational quantum circuit architectures, 2021. https://arxiv.org/abs/2103.16089.
• [26] Paszke A., Gross S., Chintala S., Chanan G., Yang E., DeVito Z., Lin Z., et al.: Automatic differentiation in PyTorch. In: NIPS-W, 2017.
• [27] Raschka S.: Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning, 2020. https://arxiv.org/abs/1811.12808.
• [28] Rybotycki T., Gawron P.: AQMLator Documentation. https : / /aqmlator.readthedocs.io/en/latest/index.html. Accessed: 2024-09-18.
• [29] Rybotycki T., Gawron P.: AQMLator PyPi page, https://pypi.org/project/AQMLator/. Accessed: 2024-09-18.
• [30] Shor P.: Algorithms for quantum computation: discrete logarithms and factoring. In: Proceedings 35th Annual Symposium on Foundations of Computer Science, pp. 124–134, 1994.
• [31] Subasi O.: Toward Automated Quantum Variational Machine Learning, 2023. https://arxiv.org/abs/2312.01567.
• [32] Xanadu Quantum Technologies: PennyLane Documentation, https : / /docs.pennylane.ai/en/stable/index.html. Accessed: 2024-09-18.