Abstract
An emerging direction of quantum computing is to establish meaningful quantum applications in various fields of artificial intelligence, including natural language processing (NLP). Although some efforts based on syntactic analysis have opened the door to research in quantum NLP (QNLP), limitations such as heavy syntactic preprocessing and syntax-dependent network architecture make them impracticable on larger and real-world data sets. In this paper, we propose a new simple network architecture, called the quantum self-attention neural network (QSANN), which can compensate for these limitations. Specifically, we introduce the self-attention mechanism into quantum neural networks and then utilize a Gaussian projected quantum self-attention serving as a sensible quantum version of self-attention. As a result, QSANN is effective and scalable on larger data sets and has the desirable property of being implementable on near-term quantum devices. In particular, our QSANN outperforms the best existing QNLP model based on syntactic analysis as well as a simple classical self-attention neural network in numerical experiments of text classification tasks on public data sets. We further show that our method exhibits robustness to low-level quantum noises and showcases resilience to quantum neural network architectures.
References
Preskill J. Quantum computing 40 years later. 2021. Ar**v:2106.10522
Harrow A W, Montanaro A. Quantum computational supremacy. Nature, 2017, 549: 203–209
Childs A M, van Dam W. Quantum algorithms for algebraic problems. Rev Mod Phys, 2010, 82: 1–52
Montanaro A. Quantum algorithms: an overview. npj Quantum Inf, 2016, 2: 15023
Childs A M, Maslov D, Nam Y, et al. Toward the first quantum simulation with quantum speedup. Proc Natl Acad Sci USA, 2018, 115: 9456–9461
Biamonte J, Wittek P, Pancotti N, et al. Quantum machine learning. Nature, 2017, 549: 195–202
Brandao F G S L, Svore K M. Quantum speed-ups for solving semidefinite programs. In: Proceedingsof the 58th Annual Symposium on Foundations of Computer Science (FOCS), 2017. 415–426
Xu F, Ma X, Zhang Q, et al. Secure quantum key distribution with realistic devices. Rev Mod Phys, 2020, 92: 25002
McArdle S, Endo S, Aspuru-Guzik A, et al. Quantum computational chemistry. Rev Mod Phys, 2020, 92: 015003
Cao Y, Romero J, Olson J P, et al. Quantum chemistry in the age of quantum computing. Chem Rev, 2019, 119: 10856–10915
Rebentrost P, Mohseni M, Lloyd S. Quantum support vector machine for big data classification. Phys Rev Lett, 2014, 113: 130503
Huang H Y, Broughton M, Mohseni M, et al. Power of data in quantum machine learning. Nat Commun, 2021, 12: 2631
Schuld M, Petruccione F. Machine Learning with Quantum Computers. Berlin: Springer, 2021
Preskill J. Quantum computing in the NISQ era and beyond. 2018. Ar**v:1801.00862
Arute F, Arya K, Babbush R, et al. Quantum supremacy using a programmable superconducting processor. Nature, 2019, 574: 505–510
Zhong H S, Wang H, Deng Y H, et al. Quantum computational advantage using photons. Science, 2020, 370: 1460–1463
Bharti K, Cervera-Lierta A, Kyaw T H, et al. Noisy intermediate-scale quantum (NISQ) algorithms. 2021. Ar**v:2101.08448
Cerezo M, Arrasmith A, Babbush R, et al. Variational quantum algorithms. Nat Rev Phys, 2021, 3: 625–644
Endo S, Cai Z, Benjamin S C, et al. Hybrid quantum-classical algorithms and quantum error mitigation. J Phys Soc Jpn, 2021, 90: 032001
Peruzzo A, McClean J, Shadbolt P, et al. A variational eigenvalue solver on a photonic quantum processor. Nat Commun, 2014, 5: 4213
Farhi E, Goldstone J, Gutmann S. A quantum approximate optimization algorithm. 2014. Ar**v:1411.4028
Havlíček V, Córcoles A D, Temme K, et al. Supervised learning with quantum-enhanced feature spaces. Nature, 2019, 567: 209–212
Schuld M, Bocharov A, Svore K M, et al. Circuit-centric quantum classifiers. Phys Rev A, 2020, 101: 032308
Mitarai K, Negoro M, Kitagawa M, et al. Quantum circuit learning. Phys Rev A, 2018, 98: 032309
Yang C H H, Qi J, Chen S Y C, et al. When bert meets quantum temporal convolution learning for text classification in heterogeneous computing. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. 8602–8606
Qi J, Tejedor J. Classical-to-quantum transfer learning for spoken command recognition based on quantum neural networks. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. 8627–8631
Yang C H H, Li B, Zhang Y, et al. A quantum kernel learning approach to acoustic modeling for spoken command recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. 1–5
Benedetti M, Lloyd E, Sack S, et al. Parameterized quantum circuits as machine learning models. Quantum Sci Technol, 2019, 4: 043001
Farhi E, Neven H. Classification with quantum neural networks on near term processors. 2018. Ar**v:1802.06002
Yu Z, Yao H S, Li M J, et al. Power and limitations of single-qubit native quantum neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 27810–27823
Caro M C, Huang H Y, Cerezo M, et al. Generalization in quantum machine learning from few training data. Nat Commun, 2022, 13: 4919
Li G X, Ye R L, Zhao X Q, et al. Concentration of data encoding in parameterized quantum circuits. In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022
Du Y, Tu Z, Yuan X, et al. Efficient measure for the expressivity of variational quantum algorithms. Phys Rev Lett, 2022, 128: 80506
Jerbi S, Fiderer L J, Nautrup H P, et al. Quantum machine learning beyond kernel methods. Nat Commun, 2023, 14: 517
Yu Z, Zhao X, Zhao B, et al. Optimal quantum dataset for learning a unitary transformation. Phys Rev Appl, 2023, 19: 034017
Wang K, Song Z, Zhao X, et al. Detecting and quantifying entanglement on near-term quantum devices. npj Quantum Inf, 2022, 8: 52
Zhao X, Zhao B, Wang Z, et al. Practical distributed quantum information processing with LOCCNet. npj Quantum Inf, 2021, 7: 159
Tian J K, Sun X Y, Du Y X, et al. Recent advances for quantum neural networks in generative learning. 2022. Ar**v:2206.03066
Wang Y, Li G, Wang X. A hybrid quantum-classical Hamiltonian learning algorithm. Sci China Inf Sci, 2023, 66: 129502
Abbas A, Sutter D, Zoufal C, et al. The power of quantum neural networks. Nat Comput Sci, 2021, 1: 403–409
Sordoni A, Nie J T, Bengio Y. Modeling term dependencies with quantum language models for IR. In: Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, New York, 2013
Zhang P, Niu J B, Su Z, et al. End-to-end quantum-like language models with application to question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Zhang Y, Song D, Zhang P, et al. A quantum-inspired sentiment representation model for twitter sentiment analysis. Appl Intell, 2019, 49: 3093–3108
Basile I, Tamburini F. Towards quantum language models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017. 1840–1849
Zeng W, Coecke B. Quantum algorithms for compositional natural language processing. 2016. Ar**v:1608.01406
Meichanetzidis K, Gogioso S, de Felice G, et al. Quantum natural language processing on near-term quantum computers. 2020. Ar**v:2005.04147
Wiebe N, Bocharov A, Smolensky P, et al. Quantum language processing. 2019. Ar**v:1902.05162
Chen S Y C, Yoo S, Fang Y L L. Quantum long short-term memory. 2020. Ar**v:2009.01783
Devlin J, Chang M W, Lee K, et al. Bert: pre-training of deep bidirectional transformers for language understanding. 2018. Ar**v:1810.04805
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017. 6000–6010
Li X P, Song J K, Gao L L, et al. Beyond RNNs: positional self-attention with co-attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2019. 8658–8665
Guo Q P, Qiu X P, Liu P F, et al. Multi-scale self-attention for text classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 7847–7854
Cha P, Ginsparg P, Wu F, et al. Attention-based quantum tomography. 2020. Ar**v:2006.12469
Lorenz R, Pearson A, Meichanetzidis K, et al. QNLP in practice: running compositional models of meaning on a quantum computer. 2021. Ar**v:2102.12846
Nielsen M A, Chuang I. Quantum Computation and Quantum Information. Cambridge: Cambridge University Press, 2011
Micchelli C A, Xu Y S, Zhang H Z. Universal kernels. J Mach Learn Res, 2006, 7: 2651–2667
Di Sipio R, Huang J H, Chen S Y C, et al. The dawn of quantum natural language processing. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. 8612–8616
Ziegel E R, Lehmann E L, Casella G. Theory of point estimation. Technometrics, 1999, 41: 274
Bottou L. Stochastic learning. In: Proceedings of Advanced Lectures on Machine Learning, 2004. 146–168
Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge: MIT Press, 2016
Liu Y, Arunachalam S, Temme K. A rigorous and robust quantum speed-up in supervised machine learning. Nat Phys, 2021, 17: 1013–1017
Qi J, Yang C H H, Chen P Y, et al. Theoretical error performance analysis for variational quantum circuit based functional regression. npj Quantum Inf, 2023, 9: 4
Kotzias D, Denil N, de Freitas N, et al. From group to individual labels using deep features. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015. 597–606
Ma Y J, Yu D H, Wu T, et al. PaddlePaddle: an open-source deep learning platform from industrial practice. Front Data Domput, 2019, 1: 105–115
Dua D, Graff C. UCI machine learning repository. 2017. http://archive.ics.uci.edu/ml
Kingma D P, Ba J L. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations, 2015
Acknowledgements
This work was partially supported by Guangdong Provincial Quantum Science Strategic Initiative (Grant No. GDZX2303007). Guangxi LI acknowledges the support from Quantum Science Center of Guangdong-Hong Kong-Macao Greater Bay Area, Baidu-UTS AI Meets Quantum project, the China Scholarship Council (Grant No. 201806070139), and Australian Research Council Project (Grant No. DP180100691). **n WANG was partially supported by Start-up Fund (Grant No. G0101000151) from The Hong Kong University of Science and Technology (Guangzhou), Innovation Program for Quantum Science and Technology (Grant No. 2021ZD0302901), and Education Bureau of Guangzhou Municipality. We would like to thank Prof. Sanjiang LI and Prof. Yuan FENG for their helpful discussions. We also thank Zihe WANG and Chenghong ZHU for their help related to the experiments. Part of this work was done when all of the authors were at Baidu Research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, G., Zhao, X. & Wang, X. Quantum self-attention neural networks for text classification. Sci. China Inf. Sci. 67, 142501 (2024). https://doi.org/10.1007/s11432-023-3879-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-023-3879-7