- Physical Review Journals
All JournalsPhysics Magazine

PRX Quantum

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Intrinsic Preservation of Plasticity in Continual Quantum Learning

Yu-Qin Chen1,* and Shi-Xin Zhang2,†

  • *Contact author: yqchen@gscaep.ac.cn
  • †Contact author: shixinzhang@iphy.ac.cn
PDF

PRX Quantum 7, 033003 – Published 6 July, 2026

DOI: https://doi.org/10.1103/ry52-85ll

Abstract

Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually lose their ability to learn from new data. Here we show that quantum learning models naturally overcome this limitation, preserving plasticity over long timescales. We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms, including supervised learning and reinforcement learning, and diverse data modalities, from classical high-dimensional images to quantum-native datasets. Although classical models exhibit performance degradation correlated with unbounded weight and gradient growth, quantum neural networks maintain consistent learning capabilities regardless of the data or task. We identify the origin of the advantage as the intrinsic physical constraints of quantum models. Unlike classical networks where unbounded weight growth leads to landscape ruggedness or saturation, the unitary constraints confine the optimization to a compact manifold. Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups, offering a robust pathway for building adaptive artificial intelligence and lifelong learners.

View figure in article

Physics Subject Headings (PhySH)

Popular Summary

Artificial intelligence needs to adapt to a changing world, yet standard deep learning models often gradually lose their capacity to learn from new data over time—a phenomenon known as loss of plasticity. We show that quantum neural networks naturally resist this degradation, preserving their learning capability indefinitely. Through extensive simulations ranging from image classification to complex reinforcement learning tasks, we demonstrate that, while classical networks become rigid and unteachable as their internal parameters grow, quantum models remain flexible due to the intrinsic physical constraints of quantum mechanics. This structural stability prevents the saturation that typically hampers long-term learning in classical systems. Our findings highlight a new dimension of quantum advantage, suggesting that quantum computing could be the key to creating sustainable, lifelong learning AI agents that can evolve continuously without needing to be retrained from scratch.

Article Text

References (58)

  1. Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature (London) 521, 436 (2015).
  2. M. I. Jordan and T. M. Mitchell, Machine learning: Trends, perspectives, and prospects, Science 349, 255 (2015).
  3. R. Bommasani et al., On the opportunities and risks of foundation models, arXiv:2108.07258.
  4. S. Bilik et al., Towards phytoplankton parasite detection using autoencoders, Mach. Vis. Appl. 34, 101 (2023), https://arxiv.org/abs/2303.08774.
  5. D. Guo et al., DeepSeek-R1 incentivizes reasoning in LLMS through reinforcement learning, Nature (London) 645, 633 (2025).
  6. E. Strubell, A. Ganesh, and A. McCallum, Energy and policy considerations for modern deep learning research, inProceedings of the AAAI Conference on Artificial Intelligence (2020), Vol. 34, p. 13693.
  7. G. Ditzler, M. Roveri, C. Alippi, and R. Polikar, Learning in nonstationary environments: A survey, IEEE Comput. Intell. Magazine 10, 12 (2015).
  8. R. Hadsell, D. Rao, A. A. Rusu, and R. Pascanu, Embracing change: Continual learning in deep neural networks, Trends Cognitive Sci. 24, 1028 (2020).
  9. L. Wang, X. Zhang, H. Su, and J. Zhu, A comprehensive survey of continual learning: Theory, method and application, IEEE Trans. Pattern Anal. Mach. Intell. 46, 5362 (2024).
  10. I. J. Goodfellow, M. Mirza, D. Xiao, A. Courville, and Y. Bengio, An empirical investigation of catastrophic forgetting in gradient-based neural networks, arXiv:1312.6211.
  11. J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, and R. Hadsell, Overcoming catastrophic forgetting in neural networks, Proc. Natl. Acad. Sci. U.S.A. 114, 3521 (2017).
  12. F. Zenke, B. Poole, and S. Ganguli, in Proceedings of the 34th International Conference on Machine Learning, ICML’17 (JMLR.org, 2017), Vol. 70, pp. 3987–3995, https://proceedings.mlr.press/v70/zenke17a.html.
  13. S. Dohare, J. F. Hernandez-Garcia, Q. Lan, P. Rahman, A. R. Mahmood, and R. S. Sutton, Loss of plasticity in deep continual learning, Nature (London) 632, 768 (2024).
  14. A. Chaudhry, P. K. Dokania, T. Ajanthan, and P. H. S. Torr, Riemannian walk for incremental learning: Understanding forgetting and intransigence (2018), pp. 556–572, 10.1007/978-3-030-01252-6_33.
  15. J. T. Ash and R. P. Adams, in Proceedings of the 34th International Conference on Neural Information Processing Systems, NeurIPS’20 (Curran Associates Inc., Red Hook, NY, 2020).
  16. T. Berariu, W. Czarnecki, S. De, J. Bornschein, S. Smith, R. Pascanu, and C. Clopath, A study on the plasticity of neural networks, arXiv:2106.00042.
  17. E. Nikishin, M. Schwarzer, P. D’Oro, P.-L. Bacon, and A. Courville, in Proceedings of the 39th International Conference on Machine Learning (PMLR, 2022), Vol. 162, pp. 16828–16847, https://proceedings.mlr.press/v162/nikishin22a.html.
  18. Z. Abbas, R. Zhao, J. Modayil, A. White, and M. C. Machado, Loss of plasticity in continual deep reinforcement learning, arXiv:2303.07507.
  19. C. Lyle, Z. Zheng, E. Nikishin, B. A. Pires, R. Pascanu, and W. Dabney, in Proceedings of the 40th International Conference on Machine Learning, ICML’23 (JMLR.org, 2023), https://proceedings.mlr.press/v202/lyle23b.html.
  20. M. Elsayed and A. R. Mahmood, Addressing loss of plasticity and catastrophic forgetting in continual learning, arXiv:2404.00781.
  21. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Quantum machine learning, Nature (London) 549, 195 (2017).
  22. S. Lloyd, M. Mohseni, and P. Rebentrost, Quantum algorithms for supervised and unsupervised machine learning, arXiv:1307.0411.
  23. M. Schuld, I. Sinayskiy, and F. Petruccione, The quest for a quantum neural network, Quantum Inf. Process. 13, 2567 (2014).
  24. H.-Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, H. Neven, and J. R. McClean, Power of data in quantum machine learning, Nat. Commun. 12, 2631 (2021).
  25. H.-Y. Huang, M. Broughton, J. Cotler, S. Chen, J. Li, M. Mohseni, H. Neven, R. Babbush, R. Kueng, J. Preskill, and J. R. McClean, Quantum advantage in learning from experiments, Science 376, 1182 (2022).
  26. M. Cerezo, G. Verdon, H.-Y. Huang, L. Cincio, and P. J. Coles, Challenges and opportunities in quantum machine learning, Nat. Comput. Sci. 2, 567 (2022).
  27. V. Havlíček, A. D. Córcoles, K. Temme, A. W. Harrow, A. Kandala, J. M. Chow, and J. M. Gambetta, Supervised learning with quantum-enhanced feature spaces, Nature (London) 567, 209 (2019).
  28. A. Pérez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Data re-uploading for a universal quantum classifier, Quantum 4, 226 (2020).
  29. J.-G. Liu and L. Wang, Differentiable learning of quantum circuit born machines, Phys. Rev. A 98, 062324 (2018).
  30. P.-L. Dallaire-Demers and N. Killoran, Quantum generative adversarial networks, Phys. Rev. A 98, 012324 (2018).
  31. B. Zhang, P. Xu, X. Chen, and Q. Zhuang, Generative quantum machine learning via denoising diffusion probabilistic models, Phys. Rev. Lett. 132, 100602 (2024).
  32. S.-X. Zhang, Z.-Q. Wan, C.-K. Lee, C.-Y. Hsieh, S. Zhang, and H. Yao, Variational quantum-neural hybrid eigensolver, Phys. Rev. Lett. 128, 120502 (2022).
  33. I. Cong, S. Choi, and M. D. Lukin, Quantum convolutional neural networks, Nat. Phys. 15, 1273 (2019).
  34. J. Li, X. Yang, X. Peng, and C.-P. Sun, Hybrid quantum-classical approach to quantum optimal control, Phys. Rev. Lett. 118, 150503 (2017).
  35. K. Beer, D. Bondarenko, T. Farrelly, T. J. Osborne, R. Salzmann, D. Scheiermann, and R. Wolf, Training deep quantum neural networks, Nat. Commun. 11, 808 (2020).
  36. H. Shen, P. Zhang, Y.-Z. You, and H. Zhai, Information scrambling in quantum neural networks, Phys. Rev. Lett. 124, 200504 (2020).
  37. L. Banchi, J. Pereira, and S. Pirandola, Generalization in quantum machine learning: A quantum information standpoint, PRX Quantum 2, 040321 (2021).
  38. W. Li and D.-L. Deng, Recent advances for quantum classifiers, Sci. China Phys. Mech. Astron. 65, 220301 (2022).
  39. P.-L. Zheng, J.-B. Wang, and Y. Zhang, Efficient and quantum-adaptive machine learning with fermion neural networks, Phys. Rev. Appl. 20, 044002 (2023).
  40. J. Jäger and R. V. Krems, Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines, Nat. Commun. 14, 576 (2023).
  41. J. Miao, C.-Y. Hsieh, and S.-X. Zhang, Neural-network-encoded variational quantum algorithms, Phys. Rev. Appl. 21, 014053 (2024).
  42. Y. Wu, J. Yao, P. Zhang, and X. Li, Randomness-enhanced expressivity of quantum neural networks, Phys. Rev. Lett. 132, 010602 (2024).
  43. W. Li, S.-X. Zhang, Z. Sheng, C. Gong, J. Chen, and Z. Shuai, Quantum machine learning of molecular energies with hybrid quantum-neural wavefunction, Digit. Discov. 4, 2697 (2025).
  44. Y.-Q. Chen and S.-X. Zhang, Superior resilience to poisoning and amenability to unlearning in quantum machine learning, arXiv:2508.02422.
  45. Z. Cui, P. Zhang, and Y. Tang, Quantum flow matching, arXiv:2508.12413.
  46. W. Jiang, Z. Lu, and D.-L. Deng, Quantum continual learning overcoming catastrophic forgetting, Chin. Phys. Lett. 39, 050303 (2022).
  47. C. Zhang et al., Quantum continual learning on a programmable superconducting processor, npj Quantum Inf. 12, 28 (2026).
  48. K. He, X. Zhang, S. Ren, and J. Sun, in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), pp. 770–778.
  49. R. Dilip, Y.-J. Liu, A. Smith, and F. Pollmann, Data compression for quantum machine learning, Phys. Rev. Res. 4, 043007 (2022).
  50. K. Shen, B. Jobst, E. Shishenina, and F. Pollmann, Classification of the fashion-MNIST dataset on a quantum computer, arXiv:2403.02405.
  51. A. Kandala, A. Mezzacapo, K. Temme, M. Takita, M. Brink, J. M. Chow, and J. M. Gambetta, Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets, Nature (London) 549, 242 (2017).
  52. V. Sitzmann, J. N. P. Martel, A. W. Bergman, D. B. Lindell, and G. Wetzstein, in Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20 (Curran Associates Inc., Red Hook, NY, 2020).
  53. A. Achille, M. Rovere, and S. Soatto, Critical learning periods in deep neural networks, arXiv:1711.08856.
  54. S. Kumar, H. Marklund, and B. V. Roy, Maintaining plasticity in continual learning via regenerative regularization, arxiv:2308.11958.
  55. E. Nikishin, J. Oh, G. Ostrovski, C. Lyle, R. Pascanu, W. Dabney, and A. Barreto, in Proceedings of the 37th International Conference on Neural Information Processing Systems, NeurIPS ’23 (Curran Associates Inc., Red Hook, NY, 2023).
  56. S.-X. Zhang, J. Allcock, Z.-Q. Wan, S. Liu, J. Sun, H. Yu, X.-H. Yang, J. Qiu, Z. Ye, Y.-Q. Chen, C.-K. Lee, Y.-C. Zheng, S.-K. Jian, H. Yao, C.-Y. Hsieh, and S. Zhang, Tensorcircuit: A quantum software framework for the NISQ era, Quantum 7, 912 (2023).
  57. https://github.com/sxzgroup/quantum-plasticity.
  58. J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Barren plateaus in quantum neural network training landscapes, Nat. Commun. 9, 4812 (2018).

Outline

Information

PRX Quantum 7, 033003– Published 6 July, 2026
  • Received 19 January 2026
  • Revised 24 March 2026
  • Accepted 21 May 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation