{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:12:36Z","timestamp":1787029956064,"version":"build-2736575974"},"reference-count":42,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T00:00:00Z","timestamp":1605571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guizhou kehe major project under Grant [2017]","award":["3001"],"award-info":[{"award-number":["3001"]}]},{"name":"Guizhou kehe major project under Grant [2019]","award":["3003"],"award-info":[{"award-number":["3003"]}]},{"name":"Guizhou kehe talent under Grant [2015]","award":["4011"],"award-info":[{"award-number":["4011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The two most important aspects of material research using deep learning (DL) or machine learning (ML) are the characteristics of materials data and learning algorithms, where the proper characterization of materials data is essential for generating accurate models. At present, the characterization of materials based on the molecular composition includes some methods based on feature engineering, such as Magpie and One-hot. Although these characterization methods have achieved significant results in materials research, these methods based on feature engineering cannot guarantee the integrity of materials characterization. One possible approach is to learn the materials characterization via neural networks using the chemical knowledge and implicit composition rules shown in large-scale known materials. This article chooses an adversarial method to learn the composition of atoms using the Generative Adversarial Network (GAN), which makes sense for data symmetry. The total loss value of the discriminator on the test set is reduced from 4.1e13 to 0.3194, indicating that the designed GAN network can well capture the combination of atoms in real materials. We then use the trained discriminator weights for material characterization and predict bandgap, formation energy, critical temperature (Tc) of superconductors on the Open Quantum Materials Database (OQMD), Materials Project (MP), and SuperCond datasets. Experiments show that when using the same predictive model, our proposed method performs better than One-hot and Magpie. This article provides an effective method for characterizing materials based on molecular composition in addition to Magpie, One-hot, etc. In addition, the generator learned in this study generates hypothetical materials with the same distribution as known materials, and these hypotheses can be used as a source for new material discovery.<\/jats:p>","DOI":"10.3390\/sym12111889","type":"journal-article","created":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T07:23:28Z","timestamp":1605597808000},"page":"1889","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Learning Representations of Inorganic Materials from Generative Adversarial Networks"],"prefix":"10.3390","volume":"12","author":[{"given":"Tiantian","family":"Hu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Song","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-6000","authenticated-orcid":false,"given":"Shaobo","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"School of Mechanical Engineering, Guizhou University, Guiyang 550025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"ref_1","unstructured":"Choo, K.Y., Hodge, R.A., Ramachandran, K.K., and Sivakumar, G. (2019). Controlling a Video Capture Device Based on Cognitive Personal Action and Image Identification. (10,178,294), U.S. Patent."},{"key":"ref_2","unstructured":"Berg, M.J., Robertson, J.C., Onderdonk, L.A., Reiser, J.M., and Corby, K.D. (2016). Object Dispenser Having a Variable Orifice and Image Identification. (9,501,887), U.S. Patent."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, S., Gao, Z., Wang, Z., and Liu, W. (2018). Real-time recognition method for 0.8 cm darning needles and KR22 bearings based on convolution neural networks and data increase. Appl. Sci., 8.","DOI":"10.3390\/app8101857"},{"key":"ref_4","unstructured":"Dusan, S.V., Lindahl, A.M., and Watson, R.D. (2019). Automatic Speech Recognition Triggering System. (10,313,782), U.S. Patent."},{"key":"ref_5","unstructured":"Malinowski, L.M., Majcher, P.J., Stemmer, G., Rozen, P., Hofer, J., and Bauer, J.G. (2019). System and Method of Automatic Speech Recognition Using Parallel Processing for Weighted Finite State Transducer-Based Speech Decoding. (10,255,911), U.S. Patent."},{"key":"ref_6","unstructured":"Juneja, A. (2017). Hybridized Client-Server Speech Recognition. (9,674,328), U.S. Patent."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Clark, K., Luong, M.-T., Khandelwal, U., Manning, C.D., and Le, Q.V. (2019). Bam! born-again multi-task networks for natural language understanding. arXiv.","DOI":"10.18653\/v1\/P19-1595"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Thomason, J., Padmakumar, A., Sinapov, J., Walker, N., Jiang, Y., Yedidsion, H., Hart, J., Stone, P., and Mooney, R.J. (2019, January 20\u201324). Improving grounded natural language understanding through human-robot dialog. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8794287"},{"key":"ref_9","unstructured":"Marcus, J.N. (2019). Initializing a Workspace for Building a Natural Language Understanding System. (10,229,106), U.S. Patent."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/JAS.2016.7471613","article-title":"Where does AlphaGo go: From church-turing thesis to AlphaGo thesis and beyond","volume":"3","author":"Wang","year":"2016","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"011002","DOI":"10.1063\/1.4812323","article-title":"Commentary: The Materials Project: A materials genome approach to accelerating materials innovation","volume":"1","author":"Jain","year":"2013","journal-title":"Apl Mater."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1501","DOI":"10.1007\/s11837-013-0755-4","article-title":"Materials design and discovery with high-throughput density functional theory: The open quantum materials database (OQMD)","volume":"65","author":"Saal","year":"2013","journal-title":"Jom"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1107\/S0108768102006948","article-title":"New developments in the Inorganic Crystal Structure Database (ICSD): Accessibility in support of materials research and design","volume":"58","author":"Belsky","year":"2002","journal-title":"Acta Crystallogr. Sect. B Struct. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4117","DOI":"10.1073\/pnas.1818555116","article-title":"Deep elastic strain engineering of bandgap through machine learning","volume":"116","author":"Shi","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","article-title":"Graph networks as a universal machine learning framework for molecules and crystals","volume":"31","author":"Chen","year":"2019","journal-title":"Chem. Mater."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"140022","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1021\/acs.jpclett.8b03527","article-title":"Creating Machine Learning-Driven Material Recipes Based on Crystal Structure","volume":"10","author":"Takahashi","year":"2019","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"16028","DOI":"10.1038\/npjcompumats.2016.28","article-title":"A general-purpose machine learning framework for predicting properties of inorganic materials","volume":"2","author":"Ward","year":"2016","journal-title":"NPJ Comput. Mater."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1002\/aic.15251","article-title":"Property prediction of crystalline solids from composition and crystal structure","volume":"62","author":"Calfa","year":"2016","journal-title":"AICHE J."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41524-018-0085-8","article-title":"Machine learning modeling of superconducting critical temperature","volume":"4","author":"Stanev","year":"2018","journal-title":"NPJ Comput. Mater."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1021\/acs.jpclett.8b00124","article-title":"Predicting the band gaps of inorganic solids by machine learning","volume":"9","author":"Zhuo","year":"2018","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9844","DOI":"10.1021\/jacs.8b02717","article-title":"Machine learning directed search for ultraincompressible, superhard materials","volume":"140","author":"Oliynyk","year":"2018","journal-title":"J. Am. Chem. Soc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/npjcompumats.2015.10","article-title":"The Open Quantum Materials Database (OQMD): Assessing the accuracy of DFT formation energies","volume":"1","author":"Kirklin","year":"2015","journal-title":"NPJ Comput. Mater."},{"key":"ref_24","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein gan. arXiv."},{"key":"ref_25","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Montreal, QC, Canada."},{"key":"ref_26","unstructured":"Doersch, C. (2016). Tutorial on variational autoencoders. arXiv."},{"key":"ref_27","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016, January 5\u201310). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Barcelona, Spain."},{"key":"ref_28","unstructured":"Fuglede, B., and Topsoe, F. (July, January 27). Jensen-Shannon divergence and Hilbert space embedding. Proceedings of the International Symposium onInformation Theory, 2004, Chicago, IL, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1107\/S0108768185002063","article-title":"Bond-valence parameters obtained from a systematic analysis of the inorganic crystal structure database","volume":"41","author":"Brown","year":"1985","journal-title":"Acta Crystallogr. Sect. B Struct. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.intermet.2017.08.004","article-title":"Dislocation dynamics in Al0. 1CoCrFeNi high-entropy alloy under tensile loading","volume":"91","author":"Sharma","year":"2017","journal-title":"Intermetallics"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.scriptamat.2017.07.024","article-title":"Crystallization kinetics in AlxCrCoFeNi (0\u2264 x\u2264 40) high-entropy alloys","volume":"141","author":"Sharma","year":"2017","journal-title":"Scr. Mater."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"31028","DOI":"10.1038\/srep31028","article-title":"Atomistic clustering-ordering and high-strain deformation of an Al 0.1 CrCoFeNi high-entropy alloy","volume":"6","author":"Sharma","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-35934-y","article-title":"Elemnet: Deep learning the chemistry of materials from only elemental composition","volume":"8","author":"Jha","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1042\/CS20150405","article-title":"The balance between IL-17 and IL-22 produced by liver-infiltrating T-helper cells critically controls NASH development in mice","volume":"130","author":"Rolla","year":"2016","journal-title":"Clin. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/79.489268","article-title":"Blind image deconvolution","volume":"13","author":"Kundur","year":"1996","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_36","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.jocs.2018.05.005","article-title":"Abnormal breast identification by nine-layer convolutional neural network with parametric rectified linear unit and rank-based stochastic pooling","volume":"27","author":"Zhang","year":"2018","journal-title":"J. Comput. Sci."},{"key":"ref_38","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv."},{"key":"ref_39","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Goodall, R.E., and Lee, A.A. (2019). Predicting materials properties without crystal structure: Deep representation learning from stoichiometry. arXiv.","DOI":"10.1038\/s41467-020-19964-7"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1016\/j.chempr.2016.09.010","article-title":"Computational screening of all stoichiometric inorganic materials","volume":"1","author":"Davies","year":"2016","journal-title":"Chem"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Dan, Y., Zhao, Y., Li, X., Li, S., Hu, M., and Hu, J. (2019). Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials. arXiv.","DOI":"10.1038\/s41524-020-00352-0"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/11\/1889\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:34:30Z","timestamp":1760178870000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/12\/11\/1889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,17]]},"references-count":42,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2020,11]]}},"alternative-id":["sym12111889"],"URL":"https:\/\/doi.org\/10.3390\/sym12111889","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,17]]}}}