|
|
|
Abstract Recent advances in quantum technology have led to the development and the manufacturing of programmable quantum annealers that promise to solve certain combinatorial optimization problems faster than their classical counterparts. Semi-supervised learning is a machine learning technique that makes use of both labeled and unlabeled data for training, which enables a good classifier with only a small amount of labeled data. In this paper, we propose and theoretically analyze a graph-based semi-supervised learning method with the aid of the quantum annealing technique, which efficiently utilizes the quantum resources while maintaining good accuracy. We illustrate two classification examples, suggesting the feasibility of this method even with a small portion (30%) of labeled data involved.
|
Received: 14 October 2020
Revised: 23 December 2020
Accepted manuscript online: 03 February 2021
|
|
PACS:
|
03.67.-a
|
(Quantum information)
|
| |
03.67.Lx
|
(Quantum computation architectures and implementations)
|
|
|
Corresponding Authors:
†Corresponding author. E-mail: wei.geng@huawei.com
|
Cite this article:
Yu-Lin Zheng(郑玉鳞), Wen Zhang(张文), Cheng Zhou(周诚), and Wei Geng(耿巍) Quantum annealing for semi-supervised learning 2021 Chin. Phys. B 30 040306
|
1 Michie D, Spiegelhalter D J and Taylor C C 1994 Machine Learning, Neural and Statistical Classification (New Jersey: Ellis Horwood ) pp. 1-6
2 Christopher M B Pattern recognition and machine learning(New York: Springer) pp. 1-4
3 Steane A 1998 Rep. Prog. Phys. 61 117
4 Hirvensalo M 2013 Quantum Computing (Springer Science & Business Media) pp. 49-71
5 Shor P 1994 Proceedings 35th annual symposium on foundations of computer science, IEEE, pp. 124-134
6 Zhang S, Duan Q H, Li T, Fu X Q, Huang H L, Wang X and Bao W S 2020 Chin. Phys. B 29 010308
7 Zheng S B 2005 Chin. Phys. 14 2222
8 Schuld M, Sinayskiy I and Petruccione F 2015 Contemp. Phys. 56 172
9 Biamonte J, Wittek P, Pancotti N, Rebentrost P, Wiebe N and Lloyd S 2017 Nature 549 195
11 Rebentrost P, Mohseni M and Lloyd S 2014 Phys. Rev. Lett. 113 130503
12 Lloyd S, Mohseni M and Rebentrost P 2014 Nat. Phys. 10 631
13 Gao X, Zhang Z Y and Duan L M 2019 Sci. Adv. 4 eaat9004
14 Preskill J Quantum 2 79
15 Neukart F, Compostella G, Seidel C, Von Dollen D, Yarkoni S and Parney B 2017 Front. ICT 4 29
16 Babbush R, Love P J and Aspuru-Guzik A 2014 Sci. Rep. 4 6603
17 Chapelle O, Scholkopf B and Zien A 2009 IEEE Trans. Nerual Netw. Learn. Syst. 20 542
19 Zhu X and Goldberg A B 2009 Synth. Lect. Artif. Intell. Mach. Learn. 3 1
20 Zhou X and Belkin M Academic Press Library in Signal Processing, Volume 1: Signal Processing Theory and Machine Learning, Chapter 22 -Semi-Supervised Learning(Amsterdam: Elsevier) pp. 1239-1269
21 Zha Z J, Mei T, Wang J D and Hua X S 2009 J. Vis. Commun. Image Represent. 20 97
22 Roweis S T and Saul L K 2000 Science 290 2323
23 Kambhatla N and Leen T K 1997 Neural Comput. 9 1493
24 Fergus R, Weiss Y and Torralba A Advances in neural information processing systems 22, December 7-10, 2009, Vancouver, British Columbia, Canada, pp. 522-530
25 Liu W, He J and Chang S F The 27th International Conference on Machine Learning, June 21-24, 2010, Haifa, Israel, 2010, pp. 1-8
26 Zhou D, Bousquet O, Lal T N and Schölkopf B Conference and Workshop on Neural Information Processing Systems December 13-18, 2004, Vancouver, British Columbia, Canada, pp. 595-602
27 Kadowaki T and Nishimori H 1998 Phys. Rev. E 58 5355
28 Bunyk P I, Hoskinson E M, Johnson M W, Tolkacheva E, Altomare F, Berkley A J, Harris R, Hilton J P, Lanting T, Przybysz A J and Whittaker J 2014 IEEE Trans. Appl. Supercond. 24 1
29 Boixo S, Albash T, Spedalieri F M, Chancellor N and Lidar D A 2013 Nat. Commun. 4 2067
30 Boixo S, Rønnow T F, Isakov S V, Wang Z, Wecker D, Lidar D A, Martinis J M and Troyer M 2014 Nat. Phys. 10 218
31 Ray P, Chakrabarti B K and Chakrabarti A 1989 Phys. Rev. B 39 11828
32 Van Dam W, Mosca M and Vazirani U In Proceedings 42nd IEEE Symposium on Foundations of Computer Science, October 8-11, 2001, Newport Beach, CA, USA, pp. 279-287
33 Kumar V, Bass G, Tomlin C and Dulny J 2018 Quantum Inf. Process. 17 39
35 Marto\vn àk R, Santoro G E and Tosatti E 2004 Phys. Rev. E 70 057701
36 Tanaka S, Matsuda Y and Togawa N 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), January 13-16, 2020, Beijing, China, pp. 659-666
37 Choi V 2008 Quantum Inf. Process. 7 193
38 Lucas A
39 Amin M H, Andryash E, Rolfe J, Kulchytskyy B and Melko R 2018 Phys. Rev. X 8 021050
40 Hinton G E and Sejnowski T J hinton/absps/pdp7.pdf1986 Parallel distributed processing: Explorations in the microstructure of cognition (Cambridge: MIT Press) 1 282-317
41 Fisher R A 1936 Ann. Eugen. 7 179
42 Kessy A, Lewin A and Strimmer, K 2018 Am. Stat. 72 309
43 Horn D and Gottlieb A 2001 Phys. Rev. Lett. 88 018702
44 Kurihara K, Tanaka S and Miyashita S 2014 arXiv:1408.2035 [quant-ph]
46 Li Z, Liu X, Xu N and Du J 2015 Phys. Rev. Lett. 114 140504 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
