IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v15y2024i1d10.1038_s41467-024-53748-7.html
   My bibliography  Save this article

Unsupervised representation learning of Kohn–Sham states and consequences for downstream predictions of many-body effects

Author

Listed:
  • Bowen Hou

    (Yale University)

  • Jinyuan Wu

    (Yale University)

  • Diana Y. Qiu

    (Yale University)

Abstract

Representation learning for the electronic structure problem is a major challenge of machine learning in computational condensed matter and materials physics. Within quantum mechanical first principles approaches, density functional theory (DFT) is the preeminent tool for understanding electronic structure, and the high-dimensional DFT wavefunctions serve as building blocks for downstream calculations of correlated many-body excitations and related physical observables. Here, we use variational autoencoders (VAE) for the unsupervised learning of DFT wavefunctions and show that these wavefunctions lie in a low-dimensional manifold within latent space. Our model autonomously determines the optimal representation of the electronic structure, avoiding limitations due to manual feature engineering. To demonstrate the utility of the latent space representation of the DFT wavefunction, we use it for the supervised training of neural networks (NN) for downstream prediction of quasiparticle bandstructures within the GW formalism. The GW prediction achieves a low error of 0.11 eV for a combined test set of two-dimensional metals and semiconductors, suggesting that the latent space representation captures key physical information from the original data. Finally, we explore the generative ability and interpretability of the VAE representation.

Suggested Citation

  • Bowen Hou & Jinyuan Wu & Diana Y. Qiu, 2024. "Unsupervised representation learning of Kohn–Sham states and consequences for downstream predictions of many-body effects," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
  • Handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-53748-7
    DOI: 10.1038/s41467-024-53748-7
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-024-53748-7
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-024-53748-7?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Yuan Cao & Valla Fatemi & Shiang Fang & Kenji Watanabe & Takashi Taniguchi & Efthimios Kaxiras & Pablo Jarillo-Herrero, 2018. "Unconventional superconductivity in magic-angle graphene superlattices," Nature, Nature, vol. 556(7699), pages 43-50, April.
    2. Rongxin Xia & Sabre Kais, 2018. "Quantum machine learning for electronic structure calculations," Nature Communications, Nature, vol. 9(1), pages 1-6, December.
    3. Xiaoxun Gong & He Li & Nianlong Zou & Runzhang Xu & Wenhui Duan & Yong Xu, 2023. "General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
    4. Simon Batzner & Albert Musaelian & Lixin Sun & Mario Geiger & Jonathan P. Mailoa & Mordechai Kornbluth & Nicola Molinari & Tess E. Smidt & Boris Kozinsky, 2022. "E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    5. Nikolaj Rørbæk Knøsgaard & Kristian Sommer Thygesen, 2022. "Representing individual electronic states for machine learning GW band structures of 2D materials," Nature Communications, Nature, vol. 13(1), pages 1-10, December.
    6. João Augusto Sobral & Stefan Obernauer & Simon Turkel & Abhay N. Pasupathy & Mathias S. Scheurer, 2023. "Machine learning the microscopic form of nematic order in twisted double-bilayer graphene," Nature Communications, Nature, vol. 14(1), pages 1-9, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Xiaoxun Gong & He Li & Nianlong Zou & Runzhang Xu & Wenhui Duan & Yong Xu, 2023. "General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
    2. Ziduo Yang & Yi-Ming Zhao & Xian Wang & Xiaoqing Liu & Xiuying Zhang & Yifan Li & Qiujie Lv & Calvin Yu-Chian Chen & Lei Shen, 2024. "Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    3. Zechen Tang & He Li & Peize Lin & Xiaoxun Gong & Gan Jin & Lixin He & Hong Jiang & Xinguo Ren & Wenhui Duan & Yong Xu, 2024. "A deep equivariant neural network approach for efficient hybrid density functional calculations," Nature Communications, Nature, vol. 15(1), pages 1-9, December.
    4. He Wang & Yanzhao Liu & Ming Gong & Hua Jiang & Xiaoyue Gao & Wenlong Ma & Jiawei Luo & Haoran Ji & Jun Ge & Shuang Jia & Peng Gao & Ziqiang Wang & X. C. Xie & Jian Wang, 2023. "Emergent superconductivity in topological-kagome-magnet/metal heterostructures," Nature Communications, Nature, vol. 14(1), pages 1-8, December.
    5. J. Díez-Mérida & A. Díez-Carlón & S. Y. Yang & Y.-M. Xie & X.-J. Gao & J. Senior & K. Watanabe & T. Taniguchi & X. Lu & A. P. Higginbotham & K. T. Law & Dmitri K. Efetov, 2023. "Symmetry-broken Josephson junctions and superconducting diodes in magic-angle twisted bilayer graphene," Nature Communications, Nature, vol. 14(1), pages 1-7, December.
    6. Yuhao Ye & Jinhua Wang & Pan Nie & Huakun Zuo & Xiaokang Li & Kamran Behnia & Zengwei Zhu & Benoît Fauqué, 2024. "Tuning the BCS-BEC crossover of electron-hole pairing with pressure," Nature Communications, Nature, vol. 15(1), pages 1-7, December.
    7. Li Chen & Cong Lin & Diwei Shi & Xuanyu Huang & Quanshui Zheng & Jinhui Nie & Ming Ma, 2023. "Fully automatic transfer and measurement system for structural superlubric materials," Nature Communications, Nature, vol. 14(1), pages 1-10, December.
    8. Xinyu Wang & Jinghua Jiang & Juan Chen & Zhawure Asilehan & Wentao Tang & Chenhui Peng & Rui Zhang, 2024. "Moiré effect enables versatile design of topological defects in nematic liquid crystals," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    9. Alejandro Ruiz & Brandon Gunn & Yi Lu & Kalyan Sasmal & Camilla M. Moir & Rourav Basak & Hai Huang & Jun-Sik Lee & Fanny Rodolakis & Timothy J. Boyle & Morgan Walker & Yu He & Santiago Blanco-Canosa &, 2022. "Stabilization of three-dimensional charge order through interplanar orbital hybridization in PrxY1−xBa2Cu3O6+δ," Nature Communications, Nature, vol. 13(1), pages 1-7, December.
    10. Sami Dzsaber & Diego A. Zocco & Alix McCollam & Franziska Weickert & Ross McDonald & Mathieu Taupin & Gaku Eguchi & Xinlin Yan & Andrey Prokofiev & Lucas M. K. Tang & Bryan Vlaar & Laurel E. Winter & , 2022. "Control of electronic topology in a strongly correlated electron system," Nature Communications, Nature, vol. 13(1), pages 1-7, December.
    11. Sahar Pakdel & Asbjørn Rasmussen & Alireza Taghizadeh & Mads Kruse & Thomas Olsen & Kristian S. Thygesen, 2024. "High-throughput computational stacking reveals emergent properties in natural van der Waals bilayers," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    12. Kaijie Yang & Zian Xu & Yanjie Feng & Frank Schindler & Yuanfeng Xu & Zhen Bi & B. Andrei Bernevig & Peizhe Tang & Chao-Xing Liu, 2024. "Topological minibands and interaction driven quantum anomalous Hall state in topological insulator based moiré heterostructures," Nature Communications, Nature, vol. 15(1), pages 1-8, December.
    13. Keshav Singh & Aaron Chew & Jonah Herzog-Arbeitman & B. Andrei Bernevig & Oskar Vafek, 2024. "Topological heavy fermions in magnetic field," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    14. Peng Wang & Qidong Fu & Ruihan Peng & Yaroslav V. Kartashov & Lluis Torner & Vladimir V. Konotop & Fangwei Ye, 2022. "Two-dimensional Thouless pumping of light in photonic moiré lattices," Nature Communications, Nature, vol. 13(1), pages 1-8, December.
    15. Avior Almoalem & Irena Feldman & Ilay Mangel & Michael Shlafman & Yuval E. Yaish & Mark H. Fischer & Michael Moshe & Jonathan Ruhman & Amit Kanigel, 2024. "The observation of π-shifts in the Little-Parks effect in 4Hb-TaS2," Nature Communications, Nature, vol. 15(1), pages 1-8, December.
    16. Märta A. Tschudin & David A. Broadway & Patrick Siegwolf & Carolin Schrader & Evan J. Telford & Boris Gross & Jordan Cox & Adrien E. E. Dubois & Daniel G. Chica & Ricardo Rama-Eiroa & Elton J. G. Sant, 2024. "Imaging nanomagnetism and magnetic phase transitions in atomically thin CrSBr," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    17. Andreas Erlebach & Martin Šípka & Indranil Saha & Petr Nachtigall & Christopher J. Heard & Lukáš Grajciar, 2024. "A reactive neural network framework for water-loaded acidic zeolites," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    18. Yuri Saida & Thomas Gauthier & Hiroo Suzuki & Satoshi Ohmura & Ryo Shikata & Yui Iwasaki & Godai Noyama & Misaki Kishibuchi & Yuichiro Tanaka & Wataru Yajima & Nicolas Godin & Gaël Privault & Tomoharu, 2024. "Photoinduced dynamics during electronic transfer from narrow to wide bandgap layers in one-dimensional heterostructured materials," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    19. Anushree Datta & M. J. Calderón & A. Camjayi & E. Bascones, 2023. "Heavy quasiparticles and cascades without symmetry breaking in twisted bilayer graphene," Nature Communications, Nature, vol. 14(1), pages 1-8, December.
    20. Xiaozhou Zan & Xiangdong Guo & Aolin Deng & Zhiheng Huang & Le Liu & Fanfan Wu & Yalong Yuan & Jiaojiao Zhao & Yalin Peng & Lu Li & Yangkun Zhang & Xiuzhen Li & Jundong Zhu & Jingwei Dong & Dongxia Sh, 2024. "Electron/infrared-phonon coupling in ABC trilayer graphene," Nature Communications, Nature, vol. 15(1), pages 1-6, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-53748-7. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.