Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification (2212.00264v3)

Published 1 Dec 2022 in quant-ph

Abstract: Machine learning is among the most widely anticipated use cases for near-term quantum computers, however there remain significant theoretical and implementation challenges impeding its scale up. In particular, there is an emerging body of work which suggests that generic, data agnostic quantum machine learning (QML) architectures may suffer from severe trainability issues, with the gradient of typical variational parameters vanishing exponentially in the number of qubits. Additionally, the high expressibility of QML models can lead to overfitting on training data and poor generalisation performance. A promising strategy to combat both of these difficulties is to construct models which explicitly respect the symmetries inherent in their data, so-called geometric quantum machine learning (GQML). In this work, we utilise the techniques of GQML for the task of image classification, building new QML models which are equivariant with respect to reflections of the images. We find that these networks are capable of consistently and significantly outperforming generic ansatze on complicated real-world image datasets, bringing high-resolution image classification via quantum computers closer to reality. Our work highlights a potential pathway for the future development and implementation of powerful QML models which directly exploit the symmetries of data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, “Quantum machine learning,” Nature, vol. 549, no. 7671, pp. 195–202, 2017.
  2. K. Beer, D. Bondarenko, T. Farrelly, T. J. Osborne, R. Salzmann, D. Scheiermann, and R. Wolf, “Training deep quantum neural networks,” Nature Communications, vol. 11, no. 1, pp. 1–6, 2020.
  3. 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, vol. 567, no. 7747, pp. 209–212, 2019.
  4. J. Romero, J. P. Olson, and A. Aspuru-Guzik, “Quantum autoencoders for efficient compression of quantum data,” Quantum Science and Technology, vol. 2, no. 4, p. 045001, 2017.
  5. P.-L. Dallaire-Demers and N. Killoran, “Quantum generative adversarial networks,” Physical Review A, vol. 98, no. 1, p. 012324, 2018.
  6. N. Killoran, T. R. Bromley, J. M. Arrazola, M. Schuld, N. Quesada, and S. Lloyd, “Continuous-variable quantum neural networks,” Physical Review Research, vol. 1, no. 3, p. 033063, 2019.
  7. M. Schuld and N. Killoran, “Quantum machine learning in feature hilbert spaces,” Physical review letters, vol. 122, no. 4, p. 040504, 2019.
  8. I. Cong, S. Choi, and M. D. Lukin, “Quantum convolutional neural networks,” Nature Physics, vol. 15, no. 12, pp. 1273–1278, 2019.
  9. M. Schuld, “Supervised quantum machine learning models are kernel methods,” arXiv preprint arXiv:2101.11020, 2021.
  10. S. L. Tsang, M. T. West, S. M. Erfani, and M. Usman, “Hybrid quantum-classical generative adversarial network for high resolution image generation,” arXiv preprint arXiv:2212.11614, 2022.
  11. Y. Liu, S. Arunachalam, and K. Temme, “A rigorous and robust quantum speed-up in supervised machine learning,” Nature Physics, vol. 17, no. 9, pp. 1013–1017, 2021.
  12. H.-Y. Huang, M. Broughton, J. Cotler, S. Chen, J. Li, M. Mohseni, H. Neven, R. Babbush, R. Kueng, J. Preskill et al., “Quantum advantage in learning from experiments,” Science, vol. 376, no. 6598, pp. 1182–1186, 2022.
  13. M. T. West, S. M. Erfani, C. Leckie, M. Sevior, L. C. Hollenberg, and M. Usman, “Benchmarking adversarially robust quantum machine learning at scale,” arXiv preprint arXiv:2211.12681, 2022.
  14. J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, “Barren plateaus in quantum neural network training landscapes,” Nature Communications, vol. 9, no. 1, pp. 1–6, 2018.
  15. Z. Holmes, K. Sharma, M. Cerezo, and P. J. Coles, “Connecting ansatz expressibility to gradient magnitudes and barren plateaus,” PRX Quantum, vol. 3, no. 1, p. 010313, 2022.
  16. M. Cerezo, A. Sone, T. Volkoff, L. Cincio, and P. J. Coles, “Cost function dependent barren plateaus in shallow parametrized quantum circuits,” Nature Communications, vol. 12, no. 1, pp. 1–12, 2021.
  17. S. Wang, E. Fontana, M. Cerezo, K. Sharma, A. Sone, L. Cincio, and P. J. Coles, “Noise-induced barren plateaus in variational quantum algorithms,” Nature Communications, vol. 12, no. 1, pp. 1–11, 2021.
  18. A. Pesah, M. Cerezo, S. Wang, T. Volkoff, A. T. Sornborger, and P. J. Coles, “Absence of barren plateaus in quantum convolutional neural networks,” Physical Review X, vol. 11, no. 4, p. 041011, 2021.
  19. T. L. Patti, K. Najafi, X. Gao, and S. F. Yelin, “Entanglement devised barren plateau mitigation,” Physical Review Research, vol. 3, no. 3, p. 033090, 2021.
  20. A. Skolik, J. R. McClean, M. Mohseni, P. van der Smagt, and M. Leib, “Layerwise learning for quantum neural networks,” Quantum Machine Intelligence, vol. 3, no. 1, pp. 1–11, 2021.
  21. T. Volkoff and P. J. Coles, “Large gradients via correlation in random parameterized quantum circuits,” Quantum Science and Technology, vol. 6, no. 2, p. 025008, 2021.
  22. E. Grant, L. Wossnig, M. Ostaszewski, and M. Benedetti, “An initialization strategy for addressing barren plateaus in parametrized quantum circuits,” Quantum, vol. 3, p. 214, 2019.
  23. S. Lu, L.-M. Duan, and D.-L. Deng, “Quantum adversarial machine learning,” Physical Review Research, vol. 2, no. 3, p. 033212, 2020.
  24. E. Noether, “Invariante variationsprobleme,” Nachrichten von der Gesellschaft der Wissenschaften zu Göttingen, Mathematisch-Physikalische Klasse, vol. 1918, pp. 235–257, 1918. [Online]. Available: http://eudml.org/doc/59024
  25. T. S. Cohen et al., “Equivariant convolutional networks,” 2021.
  26. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
  27. R. Kondor and S. Trivedi, “On the generalization of equivariance and convolution in neural networks to the action of compact groups,” in International Conference on Machine Learning.   PMLR, 2018, pp. 2747–2755.
  28. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  29. M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, “Geometric deep learning: Going beyond euclidean data,” IEEE Signal Processing Magazine, vol. 34, no. 4, pp. 18–42, 2017.
  30. M. M. Bronstein, J. Bruna, T. Cohen, and P. Veličković, “Geometric deep learning: Grids, groups, graphs, geodesics, and gauges,” arXiv preprint arXiv:2104.13478, 2021.
  31. Z. Li, H. Zheng, E. Thiede, J. Liu, and R. Kondor, “Group-equivariant neural networks with fusion diagrams,” arXiv preprint arXiv:2211.07482, 2022.
  32. B. Perozzi, R. Al-Rfou, and S. Skiena, “Deepwalk: Online learning of social representations,” in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014, pp. 701–710.
  33. J. Masci, D. Boscaini, M. Bronstein, and P. Vandergheynst, “Geodesic convolutional neural networks on riemannian manifolds,” in Proceedings of the IEEE international conference on computer vision workshops, 2015, pp. 37–45.
  34. A. Krizhevsky, G. Hinton et al., “Learning multiple layers of features from tiny images,” 2009.
  35. J. J. Meyer, M. Mularski, E. Gil-Fuster, A. A. Mele, F. Arzani, A. Wilms, and J. Eisert, “Exploiting symmetry in variational quantum machine learning,” arXiv preprint arXiv:2205.06217, 2022.
  36. M. Ragone, P. Braccia, Q. T. Nguyen, L. Schatzki, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, “Representation theory for geometric quantum machine learning,” arXiv preprint arXiv:2210.07980, 2022.
  37. Q. T. Nguyen, L. Schatzki, P. Braccia, M. Ragone, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, “Theory for equivariant quantum neural networks,” arXiv preprint arXiv:2210.08566, 2022.
  38. L. Schatzki, M. Larocca, F. Sauvage, and M. Cerezo, “Theoretical guarantees for permutation-equivariant quantum neural networks,” arXiv preprint arXiv:2210.09974, 2022.
  39. F. Sauvage, M. Larocca, P. J. Coles, and M. Cerezo, “Building spatial symmetries into parameterized quantum circuits for faster training,” arXiv preprint arXiv:2207.14413, 2022.
  40. A. Skolik, M. Cattelan, S. Yarkoni, T. Bäck, and V. Dunjko, “Equivariant quantum circuits for learning on weighted graphs,” arXiv preprint arXiv:2205.06109, 2022.
  41. M. Larocca, F. Sauvage, F. M. Sbahi, G. Verdon, P. J. Coles, and M. Cerezo, “Group-invariant quantum machine learning,” arXiv preprint arXiv:2205.02261, 2022.
  42. H. Zheng, G. S. Ravi, H. Wang, K. Setia, F. T. Chong, and J. Liu, “Benchmarking variational quantum circuits with permutation symmetry,” arXiv preprint arXiv:2211.12711, 2022.
  43. S. Yang, P. Luo, C.-C. Loy, and X. Tang, “From facial parts responses to face detection: A deep learning approach,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 3676–3684.
  44. V. Bergholm, J. Izaac, M. Schuld, C. Gogolin, M. S. Alam, S. Ahmed, J. M. Arrazola, C. Blank, A. Delgado, S. Jahangiri et al., “Pennylane: Automatic differentiation of hybrid quantum-classical computations,” arXiv preprint arXiv:1811.04968, 2018.
  45. Y. Nesterov, “A method for solving the convex programming problem with convergence rate o⁢(1/k2)𝑜1superscript𝑘2o(1/k^{2})italic_o ( 1 / italic_k start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT ),” Proceedings of the USSR Academy of Sciences, vol. 269, pp. 543–547, 1983.
Citations (22)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now