Efficient sampling for decision making in materials discovery

doi:10.1088/1674-1056/abf12d

Abstract Accelerating materials discovery crucially relies on strategies that efficiently sample the search space to label a pool of unlabeled data. This is important if the available labeled data sets are relatively small compared to the unlabeled data pool. Active learning with efficient sampling methods provides the means to guide the decision making to minimize the number of experiments or iterations required to find targeted properties. We review here different sampling strategies and show how they are utilized within an active learning loop in materials science.

Keywords: sampling methods active learning decision making material design Bayesian optimization

Received: 08 December 2020
Revised: 17 January 2021
Accepted manuscript online: 24 March 2021

PACS:	07.05.Fb	(Design of experiments)
	07.05.Mh	(Neural networks, fuzzy logic, artificial intelligence)
	81.90.+c	(Other topics in materials science)
	07.05.Tp	(Computer modeling and simulation)

Fund: Project supported by the National Key Research and Development Program of China (Grant No. 2017YFB0702401) and the National Natural Science Foundation of China (Grant Nos. 51571156, 51671157, 51621063, and 51931004).

Corresponding Authors: Turab Lookman, Dezhen Xue
E-mail: turablookman@gmail.com;xuedezhen@xjtu.edu.cn

Cite this article:

Yuan Tian(田原), Turab Lookman, and Dezhen Xue(薛德祯) Efficient sampling for decision making in materials discovery 2021 Chin. Phys. B 30 050705

[1] Batra R, Song L and Ramprasad R 2020 Nat. Rev. Mater.
[2] Gubernatis J E and Lookman T 2018 Phys. Rev. Mater. 2 120301
[3] Lu S, Zhou Q, Ouyang Y, Guo Y, Li Q and Wang J 2018 Nat. Commun. 9 3405
[4] Zhang B, Zheng X Q, Zhao T Y, Hu F X, Sun J R and Shen B G 2018 Chin. Phys. B 27 067503
[5] Wei J, Chu X, Sun X Y, Xu K, Deng H X, Chen J, Wei Z and Lei M 2019 InfoMat. 1 338
[6] Shen C, Wang C, Wei X, Li Y, Zwaag S and Xu W 2019 Acta Mater. 179 201
[7] Stanev V, Oses C, Kusne A G, Rodriguez E, Paglione J, Curtarolo S and Takeuchi I 2018 npj Comput. Mater. 4 29
[8] Im J, Lee S, Ko T W, Kim H W, Hyon Y and Chang H 2019 npj Comput. Mater. 5 37
[9] Schmidt J, Marques M R G, Botti S and Marques M A L 2019 npj Comput. Mater. 5 83
[10] Lookman T, Balachandran P V, Xue D, Hogden J and Theiler J 2017 Curr. Opin. Solid State Mater. Sci. 21 121
[11] Rajan K 2015 Annu. Rev. Mater. Sci. 45 153
[12] Lookman T, Balachandran P, Xue D, Pilania G, Shearman T, Theiler J, Gubernatis J E, Hogden J, Barros K, BenNaim E and Alexander F J 2016 Information science for materials discovery and design (Springer) 225 pp. 3–12
[13] Hill J, Mannodi-Kanakkithodi A, Ramprasad R and Meredig B 2018 Computational Materials System Design (Cham: Springer International Publishing) p. 193
[14] Tang B, Lu Y, Zhou J, Chouhan T, Wang H, Golani P, Xu M, Xu Q, Guan C and Liu Z 2020 Mater. Today 41 72
[15] Kusne A G, Yu H, Wu C, Zhang H, Hattrick-Simpers J, DeCost B, Sarker S, Oses C, Toher C, Curtarolo S, Davydov A V, Agarwal R,Bendersky L A, Li M, Mehta A and Takeuchi I 2020 Nat. Commun. 11 5966
[16] Harada M, Takeda H, Suzuki S, Nakano K, Tanibata N, Nakayama M, Karasuyama M and Takeuchi I 2020 J. Mater. Chem. A 8 15103
[17] Nugraha A S, Lambard G, Na J, Hossain M S A, Asahi T, Chaikittisilp W and Yamauchi Y 2020 J. Mater. Chem. A 8 13532
[18] Ozaki Y, Suzuki Y, Hawai T, Saito K, Onishi M and Ono K 2020 npj Comput. Mater 6 75
[19] Seko A and Ishiwata S 2020 Phys. Rev. B 101 134101
[20] Sato N, Yamashita T, Oguchi T, Hukushima K and Miyake T 2020 Phys. Rev. Materials 4 033801
[21] Fukazawa T, Harashima Y, Hou Z F and Miyake T 2020 Phys. Rev. Materials 3 053807
[22] Jain A, Hautier G, Ong S P and Persson K 2016 J. Mater. Res. 31 977
[23] Ramakrishna S, Zhang T Y, Lu W C, Qian Q, Low J S C, Yune J H R, Tan D Z L, Bressan S, Sanvito S and Kalidindi S R 2019 J. Intell. Manuf. 30 2307
[24] Rickman J, Chan H, Harmer M, Smeltzer J, Marvel C, Roy A and Balasubramanian G 2019 Nat. Commun. 10 1
[25] Ghahramani Z 2015 Nature 521 452
[26] Xue D, Balachandran P V, Yuan R, Hu T, Qian X, Dougherty E R and Lookman T 2016 Proc. Natl. Acad. Sci. USA 113 13301
[27] Tian Y, Yuan R, Xue D, Zhou Y, Wang Y, Ding X, Sun J and Lookman T 2020 Adv. Sci. 8 2003165
[28] Xue D, Balachandran P V, Hogden J, Theiler J, Xue D and Lookman T 2016 Nat. Commun. 7 11241
[29] Xue D, Xue D, Yuan R, Zhou Y, Balachandran P V, Ding X, Sun J and Lookman T 2017 Acta Mater. 125 532
[30] Balachandran P V, Xue D, Theiler J, Hogden J and Lookman T 2016 Sci. Rep. 6 19660
[31] Ramprasad R, Batra R, Pilania G, Mannodi-Kanakkithodi A and Kim C 2017 npj Comput. Mater. 3 54
[32] Settles B 2009 Active learning literature survey Computer Sciences Technical Report 1648 University of Wisconsin-Madison
[33] Settles B 2011 Active Learning and Experimental Design workshop In conjunction with AISTATS 2010 JMLR Workshop and Conference Proceedings 16:1-18
[34] Tran A, Mitchell J A, Swiler L P and Wildey T 2020 Acta Mater. 194 80
[35] Song Z, Chen X, Meng F, Cheng G, Wang C, Sun Z and Yin W J 2020 Chin. Phys. B 29 116103
[36] Wu Y, Meng Z, Wen K, Mi C, Zhang J and Zhai H 2020 Chin. Phys. Lett. 37 103201
[37] Yuan R, Tian Y, Xue D, Xue D, Zhou Y, Ding X, Sun J and Lookman T 2019 Adv. Sci. 6 1901395
[38] Yuan R, Liu Z, Balachandran P V, Xue D, Zhou Y, Ding X, Sun J, Xue D and Lookman T 2018 Adv. Mater. 30 1702884
[39] Wen C, Zhang Y, Wang C, Xue D, Bai Y, Antonov S, Dai L, Lookman T and Su Y 2019 ACTA Mater. 170 109
[40] Yuan R, Xue D, Xue D, Zhou Y, Ding X, Sun J and Lookman T 2019 IEEE T. Ultrason. Ferr. 66 394
[41] Jordan M I and Mitchell T M 2015 Science 349 255
[42] Lookman T, Balachandran P V, Xue D and Yuan R 2019 npj Comput. Mater. 5 21
[43] Theiler J and Zimmer B G 2017 Stat. Anal. Data Min. 10 211
[44] Bassman L, Rajak P, Kalia R K, Nakano A, Sha F, Sun J, Singh D J, Aykol M, Huck P, Persson K and Vashishta P 2018 npj Comput. Mater. 4 74
[45] Dehghannasiri R, Xue D, Balachandran P V, Yousefi M R, Dalton L A, Lookman T and Dougherty E R 2017 Comput. Mater. Sci. 129 311
[46] Gastelum J C V and Strachan A 2020 Citrine tools for materials informatics
[47] Lookman T, Balachandran P V, Xue D, Hogden J and Theiler J 2017 Curr. Opin. Solid State Mater. Sci. 21 121
[48] Awasthi P, Feldman V and Kanade V 2012 J. Mach. Learn Res. 30
[49] Tadepalli P and Russell S 1998 Mach. Learn. 32 245
[50] Shokri R, Stronati M, Song C and Shmatikov V 2017 2017 IEEE Symposium on Security and Privacy (SP) (San Jose CA: EEE) pp. 3–18
[51] Hoffmann A G and Informatik F 1990 ECAI pp. 345–347
[52] Krishnamurthy V 2002 IEEE Trans. Signal Process. 50 1382
[53] Settles B and Craven M 2008 2008 Conference on Empirical Methods in Natural Language Processing, EMNLP 2008, Proceedings of the Conference, October 25–27, 2008, Honolulu, Hawaii, USA, A meeting of SIGDAT, a Special Interest Group of the ACL
[54] Hauptmann A G, Lin W H, Yan R, Yang J and Chen M Y 2006 Association for Computing Machinery p. 385
[55] Seung H S, Opper M and Sompolinsky H 1992 Proceedings of the fifth annual workshop on Computational learning theory pp. 287–294
[56] Freund Y, Seung H S, Shamir E and Tishby N 1997 Mach. Learn. 28 133
[57] Pasolli E and Melgani F 2010 IEEE Trans. Inform. Technol. Biomed. 14 1405
[58] Kee S, del Castillo E and Runger G 2018 Inf. Sci. 454-455 401
[59] Dagan I and Engelson S P 1995 1995 Machine Learning Proceedings 1995 (San Francisco (CA): Morgan Kaufmann) pp. 150–157
[60] Xu Z, Akella R and Zhang Y 2007 Advances in Information Retrieval (Berlin Heidelberg: Springer) pp. 246–257
[61] Lafferty J and Zhai C 2001 Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (New York, NY, USA: Association for Computing Machinery) pp. 111–119
[62] Burbidge R, Rowland J J and King R D 2007 Intelligent Data Engineering and Automated Learning-IDEAL 2007 (Berlin, Heidelberg: Springer ) pp. 209–218
[63] Abe N and Mamitsuka H 1998 Proceedings of the 15th International Conference on Machine Learning (ICML) pp. 1–9
[64] Campbell C, Cristianini N, Smola A, et al. 2000 ICML 20 0
[65] Tuia D, Volpi M, Copa L, Kanevski M and Munoz-Mari J 2011 IEEE Journal of Selected Topics in Signal Processing 5 606
[66] Terayama K, Tamura R, Nose Y, Hiramatsu H, Hosono H, Okuno Y and Tsuda K 2019 Phys. Rev. Mater. 3 033802
[67] Scheffer T, Decomain C and Wrobel S 2001 International Symposium on Intelligent Data Analysis (Springer) pp. 309–318
[68] Shannon C E 1948 Bell Syst. Tech. J. 27 379
[69] Yoon B J, Qian X and Dougherty E R 2013 IEEE Trans. Signal Process. 61 2256
[70] Boluki S, Qian X and Dougherty E R 2018 IEEE Access 7 2223
[71] Imani M, Dehghannasiri R, Braga-Neto U M and Dougherty E R 2018 Cancer Inform. 17 1176935118790247
[72] Dehghannasiri R, Xue D, Balachandran P V, Yousefi M R, Dalton L A, Lookman T and Dougherty E R 2017 Comput. Mater. Sci. 129 311
[73] Thrun S B 1992 Efficient exploration in reinforcement learning tech. rep. USA
[74] Whitehead S 1991 A study of cooperative mechanisms for faster reinforcement learning
[75] Efron B 2014 J. Am. Stat. Assoc. 109 991
[76] Wager S, Hastie T and Efron B 2014 J. Mach. Learn Res. 15 1625
[77] Beyaztas U and Alin A 2014 Stat Papers 55 1001
[78] Brokampa C, Rao M B, Ryan P and Jandarov R 2017 STAT 6 360
[79] Tian Y, Yuan R, Xue D, Zhou Y, Ding X, Sun J and Lookman T 2020 J. Appl. Phys. 128 014103
[80] Tian Y, Xue D, Yuan R, Zhou Y, Ding X, Sun J and Lookman T 2021 Phys. Rev. Mater. 5 013802
[81] Bisbo M and Hammer B 2019 arXiv:1907.05741v1 [physics.chem-ph]
[82] Jones D, Schonlau M and Welch W 1998 J. Glob. Optim. 13 455
[83] Ryzhov I O, Powell W B and Frazier P I 2012 Oper. Res. 60 180
[84] Powell W 2011 The Knowledge Gradient for Optimal Learning
[85] Frazier P, Powell W and Dayanik S 2009 Informs. J. Comput. 21 599
[86] Frazier P I, Powell W B and Dayanik S 2008 SIAM J. Control. Optim. 47 2410
[87] Chen Y, Tian Y, Zhou Y, Fang D, Ding X, Sun J and Xue D 2020 J. Alloys Compd. 844 156159

[1]	Machine learning in materials design: Algorithm and application Zhilong Song(宋志龙), Xiwen Chen(陈曦雯), Fanbin Meng(孟繁斌), Guanjian Cheng(程观剑), Chen Wang(王陈), Zhongti Sun(孙中体), and Wan-Jian Yin(尹万健). Chin. Phys. B, 2020, 29(11): 116103.
[2]	Discovery and design of lithium battery materials via high-throughput modeling Xuelong Wang(王雪龙), Ruijuan Xiao(肖睿娟), Hong Li(李泓), Liquan Chen(陈立泉). Chin. Phys. B, 2018, 27(12): 128801.
[3]	Physical mechanism of mind changes and tradeoffs among speed, accuracy, and energy cost in brain decision making: Landscape, flux, and path perspectives Han Yan(闫晗), Kun Zhang(张坤), Jin Wang(汪劲). Chin. Phys. B, 2016, 25(7): 078702.
[4]	Multi-scale computation methods: Their applications in lithium-ion battery research and development Siqi Shi(施思齐), Jian Gao(高健), Yue Liu(刘悦), Yan Zhao(赵彦), Qu Wu(武曲), Wangwei Ju(琚王伟), Chuying Ouyang(欧阳楚英), Ruijuan Xiao(肖睿娟). Chin. Phys. B, 2016, 25(1): 018212.
[5]	A simple theoretical model for evaluating the ability to form a single crystal Jin Yun-Fei(金云飞), Ming Chen(明辰), Ye Xiang-Xi(叶祥熙), Wang Wei-Min(王为民), and Ning Xi-Jing(宁西京). Chin. Phys. B, 2010, 19(7): 076105.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Efficient sampling for decision making in materials discovery

Cite this article:

Online attention