{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:08:47Z","timestamp":1767773327709,"version":"3.37.3"},"reference-count":54,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"tdm","delay-in-days":1,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Over the past decades, density functional theory (DFT) calculations have been utilized in various fields such as materials science and semiconductor devices. However, due to the inherent nature of DFT calculations, which rigorously consider interactions between atoms, they require significant computational cost. To address this, extensive research has recently focused on training neural networks to replace DFT calculations. However, previous methods for training neural networks necessitated an extensive number of DFT simulations to acquire the ground truth (Hamiltonians). Conversely, when dealing with a limited amount of training data, deep learning models often display increased errors in predicting Hamiltonians and band structures for testing data. This phenomenon poses the potential risk of generating inaccurate physical interpretations, including the emergence of unphysical branches within band structures. To tackle this challenge, we propose a novel deep learning-based method for calculating DFT Hamiltonians, specifically tailored to produce accurate results with limited training data. Our framework not only employs supervised learning with the calculated Hamiltonian but also generates pseudo Hamiltonians (targets for unlabeled data) and trains the neural networks on unlabeled data. Particularly, our approach, which leverages unlabeled data, is noteworthy as it marks the first attempt in the field of neural network Hamiltonians. Our framework showcases the superior performance of our framework compared to the state-of-the-art approach across various datasets, such as MoS<jats:sub>2<\/jats:sub>, Bi<jats:sub>2<\/jats:sub>Te<jats:sub>3<\/jats:sub>, HfO<jats:sub>2<\/jats:sub>, and InGaAs. Moreover, our framework demonstrates enhanced generalization performance by effectively utilizing unlabeled data, achieving noteworthy results when evaluated on data more complex than the training set, such as configurations with more atoms and temperature ranges outside the training data.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad7227","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:10:39Z","timestamp":1724281839000},"page":"035060","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SemiH: DFT Hamiltonian neural network training with semi-supervised learning"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6634-3183","authenticated-orcid":true,"given":"Yucheol","family":"Cho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5099-1492","authenticated-orcid":true,"given":"Guenseok","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7586-2025","authenticated-orcid":true,"given":"Gyeongdo","family":"Ham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6270-5343","authenticated-orcid":true,"given":"Mincheol","family":"Shin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9131-8086","authenticated-orcid":true,"given":"Daeshik","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"mlstad7227bib1","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1103\/RevModPhys.87.897","article-title":"Density functional theory: its origins, rise to prominence and future","volume":"87","author":"Jones","year":"2015","journal-title":"Rev. Mod. Phys."},{"key":"mlstad7227bib2","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1021\/acsmaterialsau.1c00034","article-title":"First-principles calculations of luminescence spectra of real-scale quantum dots","volume":"2","author":"Kang","year":"2021","journal-title":"ACS Mater. Au"},{"article-title":"Deepgreen: equivariant neural network for green\u2019s functions of molecules and materials","year":"2023","author":"Dong","key":"mlstad7227bib3"},{"key":"mlstad7227bib4","doi-asserted-by":"publisher","first-page":"5901","DOI":"10.1109\/TED.2021.3112395","article-title":"First-principles-based quantum transport simulations of interfacial point defect effects on inas nanowire tunnel fets","volume":"68","author":"Lee","year":"2021","journal-title":"IEEE Trans. Electron Devices"},{"key":"mlstad7227bib5","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1016\/j.drudis.2021.12.017","article-title":"Applications of density functional theory in covid-19 drug modeling","volume":"27","author":"Naike","year":"2022","journal-title":"Drug Discov. Today"},{"key":"mlstad7227bib6","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1038\/s41467-023-36628-4","article-title":"A density functional theory for ecology across scales","volume":"14","author":"Trappe","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad7227bib7","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1038\/s43588-022-00265-6","article-title":"Deep-learning density functional theory hamiltonian for efficient ab initio electronic-structure calculation","volume":"2","author":"Li","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"mlstad7227bib8","first-page":"pp 14434","article-title":"Se (3)-equivariant prediction of molecular wavefunctions and electronic densities","volume":"vol 34","author":"Unke","year":"2021"},{"key":"mlstad7227bib9","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1126\/science.abj6511","article-title":"Pushing the frontiers of density functionals by solving the fractional electron problem","volume":"374","author":"Kirkpatrick","year":"2021","journal-title":"Science"},{"key":"mlstad7227bib10","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/accb26","article-title":"Efficient determination of the hamiltonian and electronic properties using graph neural network with complete local coordinates","volume":"4","author":"Mao","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad7227bib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.126403","article-title":"Learning the exchange-correlation functional from nature with fully differentiable density functional theory","volume":"127","author":"Kasim","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib12","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1021\/acs.accounts.0c00868","article-title":"Development of multimodal machine learning potentials: toward a physics-aware artificial intelligence","volume":"54","author":"Zubatiuk","year":"2021","journal-title":"Acc. Chem. Res."},{"article-title":"Neural-network density functional theory","year":"2024","author":"Yang","key":"mlstad7227bib13"},{"key":"mlstad7227bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401","article-title":"Generalized neural-network representation of high-dimensional potential-energy surfaces","volume":"98","author":"Behler","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.143001","article-title":"Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics","volume":"120","author":"Zhang","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib16","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1021\/acscentsci.8b00551","article-title":"Transferable machine-learning model of the electron density","volume":"5","author":"Grisafi","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"mlstad7227bib17","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41524-019-0162-7","article-title":"Solving the electronic structure problem with machine learning","volume":"5","author":"Chandrasekaran","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstad7227bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.206401","article-title":"Quantum deep field: data-driven wave function, electron density generation and atomization energy prediction and extrapolation with machine learning","volume":"125","author":"Tsubaki","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib19","article-title":"QH9: a quantum hamiltonian prediction benchmark for QM9 molecules","volume":"vol 36","author":"Haiyang","year":"2024"},{"key":"mlstad7227bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.132.096401","article-title":"Deep-learning density functional perturbation theory","volume":"132","author":"Li","year":"2024","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s43588-024-00632-5","article-title":"Designing semiconductor materials and devices in the post-moore era by tackling computational challenges with data-driven strategies","volume":"4","author":"Xie","year":"2024","journal-title":"Nat. Comput. Sci."},{"article-title":"Deeph-2: enhancing deep-learning electronic structure via an equivariant local-coordinate transformer","year":"2024","author":"Wang","key":"mlstad7227bib22"},{"key":"mlstad7227bib23","doi-asserted-by":"publisher","first-page":"B864","DOI":"10.1103\/PhysRev.136.B864","article-title":"Inhomogeneous electron gas","volume":"136","author":"Hohenberg","year":"1964","journal-title":"Phys. Rev."},{"key":"mlstad7227bib24","doi-asserted-by":"publisher","first-page":"A1133","DOI":"10.1103\/PhysRev.140.A1133","article-title":"Self-consistent equations including exchange and correlation effects","volume":"140","author":"Kohn","year":"1965","journal-title":"Phys. Rev."},{"key":"mlstad7227bib25","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s41524-020-00490-5","article-title":"Machine learning method for tight-binding hamiltonian parameterization from ab-initio band structure","volume":"7","author":"Wang","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstad7227bib26","doi-asserted-by":"publisher","DOI":"10.1063\/5.0023980","article-title":"Machine learning approach to constructing tight binding models for solids with application to bitecl","volume":"128","author":"Mohammad Nakhaee","year":"2020","journal-title":"J. Appl. Phys."},{"key":"mlstad7227bib27","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.scib.2021.09.010","article-title":"Neural network representation of electronic structure from ab initio molecular dynamics","volume":"67","author":"Qiangqiang","year":"2022","journal-title":"Sci. Bull."},{"key":"mlstad7227bib28","doi-asserted-by":"publisher","DOI":"10.1038\/srep42669","article-title":"Machine-learned approximations to density functional theory hamiltonians","volume":"7","author":"Hegde","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstad7227bib29","first-page":"pp 1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"article-title":"Directional message passing for molecular graphs","year":"2020","author":"Gasteiger","key":"mlstad7227bib30"},{"key":"mlstad7227bib31","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3eb3","article-title":"Calibrated uncertainty for molecular property prediction using ensembles of message passing neural networks","volume":"3","author":"Busk","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad7227bib32","first-page":"pp 6790","article-title":"Gemnet: universal directional graph neural networks for molecules","volume":"vol 34","author":"Gasteiger","year":"2021"},{"key":"mlstad7227bib33","first-page":"pp 9377","article-title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","author":"Sch\u00fctt","year":"2021"},{"key":"mlstad7227bib34","doi-asserted-by":"publisher","first-page":"2848","DOI":"10.1038\/s41467-023-38468-8","article-title":"General framework for e (3)-equivariant neural network representation of density functional theory hamiltonian","volume":"14","author":"Gong","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad7227bib35","first-page":"pp 596","article-title":"Fixmatch: simplifying semi-supervised learning with consistency and confidence","volume":"vol 33","author":"Sohn","year":"2020"},{"key":"mlstad7227bib36","first-page":"p 32","article-title":"Mixmatch: a holistic approach to semi-supervised learning","author":"Berthelot","year":"2019"},{"key":"mlstad7227bib37","first-page":"p 896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","author":"Lee","year":"2013"},{"article-title":"Semi-supervised learning of hierarchical representations of molecules using neural message passing","year":"2017","author":"Nguyen","key":"mlstad7227bib38"},{"key":"mlstad7227bib39","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1016\/j.procs.2023.08.184","article-title":"Self-supervised learning with atom replacement for catalyst energy prediction by graph neural networks","volume":"222","author":"Sakai","year":"2023","journal-title":"Proc. Comput. Sci."},{"key":"mlstad7227bib40","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.67.155108","article-title":"Variationally optimized atomic orbitals for large-scale electronic structures","volume":"67","author":"Ozaki","year":"2003","journal-title":"Phys. Rev. B"},{"key":"mlstad7227bib41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.69.195113","article-title":"Numerical atomic basis orbitals from h to KR","volume":"69","author":"Ozaki","year":"2004","journal-title":"Phys. Rev. B"},{"key":"mlstad7227bib42","doi-asserted-by":"publisher","DOI":"10.1063\/1.5019779","article-title":"Schnet\u2013a deep learning architecture for molecules and materials","volume":"148","author":"Sch\u00fctt","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstad7227bib43","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","volume":"107","author":"Elfwing","year":"2018","journal-title":"Neural Netw."},{"article-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"mlstad7227bib44"},{"key":"mlstad7227bib45","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/6173.003.0013","article-title":"Entropy regularization","author":"Grandvalet","year":"2006"},{"key":"mlstad7227bib46","doi-asserted-by":"publisher","first-page":"3045","DOI":"10.1109\/TPAMI.2017.2771779","article-title":"Visual and semantic knowledge transfer for large scale semi-supervised object detection","volume":"40","author":"Tang","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstad7227bib47","doi-asserted-by":"publisher","first-page":"3115","DOI":"10.1007\/s13042-019-01003-7","article-title":"Pkgcn: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning","volume":"10","author":"Shaowei","year":"2019","journal-title":"Int. J. Mach. Learni. Cybern."},{"article-title":"Knowledge distillation and data selection for semi-supervised learning in ctc acoustic models","year":"2020","author":"Swarup","key":"mlstad7227bib48"},{"article-title":"Harnessing deep neural networks with logic rules","year":"2016","author":"Zhiting","key":"mlstad7227bib49"},{"key":"mlstad7227bib50","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.3390\/e25091274","article-title":"A semi-supervised stacked autoencoder using the pseudo label for classification tasks","volume":"25","author":"Lai","year":"2023","journal-title":"Entropy"},{"key":"mlstad7227bib51","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s00530-017-0571-8","article-title":"Pseudo-positive regularization for deep person re-identification","volume":"24","author":"Zhu","year":"2018","journal-title":"Multimedia Syst."},{"key":"mlstad7227bib52","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","article-title":"Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set","volume":"54","author":"Kresse","year":"1996","journal-title":"Phys. Rev. B"},{"key":"mlstad7227bib53","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","article-title":"Generalized gradient approximation made simple","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"mlstad7227bib54","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1103\/PhysRevB.43.1993","article-title":"Efficient pseudopotentials for plane-wave calculations","volume":"43","author":"Troullier","year":"1991","journal-title":"Phys. Rev. B"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T10:47:11Z","timestamp":1725274031000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,1]]},"references-count":54,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,9,2]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad7227","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,9,1]]},"assertion":[{"value":"SemiH: DFT Hamiltonian neural network training with semi-supervised learning","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-04-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-21","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-09-02","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}