[1]韩思予,贾林瀚,李宇峰.稳健的量子重上传分类器[J].智能系统学报,2026,21(3):617-626.[doi:10.11992/tis.202507029]
HAN Siyu,JIA Linhan,LI Yufeng.Robust data re-uploading quantum model[J].CAAI Transactions on Intelligent Systems,2026,21(3):617-626.[doi:10.11992/tis.202507029]
点击复制
HAN Siyu,JIA Linhan,LI Yufeng.Robust data re-uploading quantum model[J].CAAI Transactions on Intelligent Systems,2026,21(3):617-626.[doi:10.11992/tis.202507029]
稳健的量子重上传分类器
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第3期
页码:
617-626
栏目:
学术论文—机器学习
出版日期:
2026-05-05
- Title:
- Robust data re-uploading quantum model
- Keywords:
- quantum machine learning; data re-uploading; regularization; overfitting; robustness; quantum computing; quantum neural network; variational quantum circuit
- 分类号:
- TP18
- 文献标志码:
- 2026-3-18
- 摘要:
- 针对数据重上传模型在实际应用中仍面临严重的过拟合与超参数敏感性问题，本研究提出了稳健重上传分类器。它通过一种创新的损失函数设计，在传统的量子态保真度基础上引入了正则化项，从而有效抑制过拟合现象并增强模型的泛化性能与稳健性。实验结果充分证明了稳健重上传分类器在降低过拟合风险、增强模型稳健性方面的显著优势。这种创新不仅为量子机器学习中损失函数的设计开拓了新路径，也为分类任务的泛化能力研究提供了新的实验依据，为未来量子机器学习的进一步发展奠定了实践基础。
- Abstract:
- To address the severe overfitting and hyperparameter sensitivity problem of the data re-uploading model, we introduce the robust quantum re-uploading classifier, featuring an innovative loss function that combines quantum state fidelity with a strategically designed regularization term. This combination effectively reduces overfitting and considerably enhances model stability and generalization. Experimental results on benchmark datasets clearly demonstrate the classifier’s superiority over existing methods, particularly in mitigating overfitting and sustaining robust predictions. Consequently, this novel strategy not only opens new avenues for designing loss functions in QML but also provides empirical insights into generalization capabilities. It establishes a strong foundation for future quantum classification research and applications.
- 参考文献/References:
-
[1] 石金晶, 肖子萌, 王雯萱, 等. 面向含噪中规模量子处理器的量子机器学习[J]. 计算机学报, 2025, 48(3): 602-631 SHI Jinjing, XIAO Zimeng, WANG Wenxuan, et al. Quantum machine learning with noisy intermediate-scale quantum processors[J]. Chinese journal of computers, 2025, 48(3): 602-631
[2] 侯敏. 量子机器学习算法研究概述[J]. 通讯世界, 2024, 31(8): 139-141 HOU Min. Overview of quantum machine learning algorithms[J]. Telecom world, 2024, 31(8): 139-141
[3] 王健, 张蕊, 姜楠. 量子机器学习综述[J]. 软件学报, 2024, 35(8): 3843-3877 WANG Jian, ZHANG Rui, JIANG Nan. Survey on quantum machine learning[J]. Journal of software, 2024, 35(8): 3843-3877
[4] 瞿治国, 陈韦龙, 孙乐, 等. ECG-QGAN: 基于量子生成对抗网络的心电图生成式信息系统[J]. 计算机研究与发展, 2025, 62(7): 1622-1638 QU Zhiguo, CHEN Weilong, SUN Le, et al. ECG-QGAN: an ECG generative information system based on quantum generative adversarial networks[J]. Journal of computer research and development, 2025, 62(7): 1622-1638
[5] 于瑞祺, 张鑫云, 任爽. 基于变分量子电路的量子机器学习算法综述[J]. 计算机研究与发展, 2025, 62(4): 821-851 YU Ruiqi, ZHANG Xinyun, REN Shuang. A review of quantum machine learning algorithms based on variational quantum circuit[J]. Journal of computer research and development, 2025, 62(4): 821-851
[6] BIAMONTE J, WITTEK P, PANCOTTI N, et al. Quantum machine learning[J]. Nature, 2017, 549(7671): 195-202
[7] CEREZO M, VERDON G, HUANG H Y, et al. Challenges and opportunities in quantum machine learning[J]. Nature computational science, 2022, 2(9): 567-576
[8] TYCHOLA K A, KALAMPOKAS T, PAPAKOSTAS G A. Quantum machine learning: an overview[J]. Electronics, 2023, 12(11): 2379
[9] ZEGUENDRY A, JARIR Z, QUAFAFOU M. Quantum machine learning: a review and case studies[J]. Entropy, 2023, 25(2): 287
[10] HAVL??EK V, C?RCOLES A D, TEMME K, et al. Supervised learning with quantum-enhanced feature spaces[J]. Nature, 2019, 567(7747): 209-212
[11] JERBI S, FIDERER L J, POULSEN NAUTRUP H, et al. Quantum machine learning beyond kernel methods[J]. Nature communications, 2023, 14: 517
[12] JERBI S, GYURIK C, MARSHALL S C, et al. Shadows of quantum machine learning[J]. Nature communications, 2024, 15: 5676
[13] SCHULD M, SWEKE R, MEYER J J. Effect of data encoding on the expressive power of variational quantum-machine-learning models[J]. Physical review A, 2021, 103(3): 032430
[14] CARO M C, GIL-FUSTER E, MEYER J J, et al. Encoding-dependent generalization bounds for parametrized quantum circuits[J]. Quantum, 2021, 5: 582
[15] CARO M C, HUANG H Y, CEREZO M, et al. Generalization in quantum machine learning from few training data[J]. Nature communications, 2022, 13: 4919
[16] KAVITHA S S, KAULGUD N. Quantum machine learning for support vector machine classification[J]. Evolutionary intelligence, 2024, 17(2): 819-828
[17] KITAEV A. Quantum computations: algorithms and error correction[J]. Russian mathematical surveys, 1997, 52(6): 1191-1249
[18] REBENTROST P, MOHSENI M, LLOYD S. Quantum support vector machine for big data classification[J]. Physical review letters, 2014, 113(13): 130503
[19] LLOYD S, SCHULD M, IJAZ A, et al. Quantum embeddings for machine learning[EB/OL]. (2020-01-10)[2025-01-01]. https://arxiv.org/abs/2001.03622.
[20] HARROW A W, HASSIDIM A, LLOYD S. Quantum algorithm for linear systems of equations[J]. Physical review letters, 2009, 103(15): 150502
[21] CONG I, CHOI S, LUKIN M D. Quantum convolutional neural networks[J]. Nature physics, 2019, 15(12): 1273-1278
[22] SCHREIBER F J, EISERT J, MEYER J J. Classical surrogates for quantum learning models[J]. Physical review letters, 2023, 131(10): 100803
[23] HUANG H Y, KUENG R, PRESKILL J. Predicting many properties of a quantum system from very few measurements[J]. Nature physics, 2020, 16(10): 1050-1057
[24] GHOBADI R, OBEROI J S, ZAHEDINEJHAD E. The power of one qubit in machine learning[EB/OL]. (2019-03-03)[2025-01-01]. https://arxiv.org/abs/1905.01390.
[25] HUANG H Y, BROUGHTON M, MOHSENI M, et al. Power of data in quantum machine learning[J]. Nature communications, 2021, 12: 2631
[26] LAROSE R, COYLE B. Robust data encodings for quantum classifiers[J]. Physical review A, 2020, 102(3): 032420
[27] GUALA D, ZHANG Shaoming, CRUZ E, et al. Practical overview of image classification with tensor-network quantum circuits[J]. Scientific reports, 2023, 13: 4427
[28] P?REZ-SALINAS A, CERVERA-LIERTA A, GIL-FUSTER E, et al. Data re-uploading for a universal quantum classifier[J]. Quantum, 2020, 4: 226
[29] BOWLES J, AHMED S, SCHULD M. Better than classical? The subtle art of benchmarking quantum machine learning models[EB/OL]. (2024-03-11)[2025-01-01]. https://arxiv.org/abs/2403.07059.
[30] HAN Siyu, JIA Lihan, GUO Lanzhe. Multiple embeddings for quantum machine learning[EB/OL]. (2025-03-27)[2025-07-01]. https://arxiv.org/abs/2503.22758.
备注/Memo
收稿日期:2025-7-27。
基金项目:国家自然科学基金项目(62576162)；中央高校基本科研业务费专项经费项目(022114380023).
作者简介:韩思予，硕士研究生，主要研究方向为机器学习、数据挖掘。曾担任ICML、IJCAI等人工智能领域著名学术会议审稿人。E-mail：hansy@lamda.nju.edu.cn。;贾林瀚，博士研究生，主要研究方向为机器学习、数据挖掘。曾担任ICML、ICLR、NeurIPS等人工智能领域著名学术会议审稿人，曾获国家奖学金、南京大学优秀研究生、中国计算机学会优秀大学生等荣誉。发表学术论文8篇。E-mail：jialh@lamda.nju.edu.cn。;李宇峰， 教授，博士生导师，国家级人才，中国计算机学会杰出会员，主要研究方向为机器学习、数据挖掘。担任中国人工智能学会机器学习专委秘书长，人工智能领域著名国际期刊《Artificial Intelligence》《Machine Learning》编委，《Frontiers of Computer Science》《计算机研究与发展》青年编委。入选人工智能旗舰国际会议IJCAI21青年成就亮点报告，获江苏省科学技术一等奖、吴文俊人工智能优博指导教师、华为火花奖等科研奖励。发表学术论文90余篇，获国内外优秀论文奖4次。E-mail：liyf@nju.edu.cn。
通讯作者:李宇峰. E-mail：liyf@nju.edu.cn
更新日期/Last Update:
1900-01-01