arxiv: 2604.15985 · v1 · submitted 2026-04-17 · ❄️ cond-mat.mes-hall

Recognition: unknown

Machine Learning and Deep Learning in Quantum Materials: Symmetry, Topology, and the Rise of Altermagnets

Hosein Alavi-Rad, Mahyar Hassani-Vasmejani, Meysam Bagheri Tagani

Authors on Pith no claims yet

Pith reviewed 2026-05-10 08:02 UTC · model grok-4.3

classification ❄️ cond-mat.mes-hall

keywords machine learningdeep learningquantum materialsaltermagnetstopologysymmetrygraph neural networks

0 comments

The pith

Symmetry-aware AI search engines have identified d-wave, g-wave, and i-wave altermagnets, expanding the landscape of magnetic order in quantum materials.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper is a review examining how machine learning and deep learning overcome the cubic scaling limits of density functional theory when searching large chemical spaces of quantum materials. It describes the move toward flexible, symmetry-respecting architectures such as E(3)-equivariant graph neural networks that maintain rotational and translational invariance. The central example shows these tools, paired with graph theory and crystallographic symmetry analysis, automatically diagnosing topological phases and locating new altermagnetic orders. A sympathetic reader cares because the approach replaces slow manual or exhaustive computations with scalable screening that can surface materials with useful electronic or magnetic properties. The review closes by noting the remaining interpretability gap and the value of symbolic regression to connect predictions to measurable mechanisms.

Core claim

The review establishes that machine learning models incorporating physical symmetries can efficiently identify topological phases via symmetry indicators and have revealed altermagnets as a third class of magnetism, including previously unknown d-wave, g-wave, and i-wave variants found through automated graph-based symmetry searches.

What carries the argument

Specialized AI search engines that combine graph theory with crystallographic symmetry analysis to detect unconventional magnetic orders beyond the ferromagnetic-antiferromagnetic dichotomy.

If this is right

High-throughput exploration of quantum materials becomes feasible at scales where DFT is impractical.
Topological character can be diagnosed from symmetry data without full band-structure integrations.
The taxonomy of magnetic order now includes altermagnets with higher multipole spin waves as a standard category.
Active-learning loops and symbolic regression can link model outputs to experimentally testable mechanisms.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same symmetry-aware search strategy could be applied to locate other protected phases such as topological superconductors or Weyl nodes.
Coupling the models to real-time experimental feedback would allow iterative refinement of predictions for device-relevant materials.
If the higher-wave altermagnets prove stable, they may enable new spintronic or magnonic devices that exploit their unique symmetry-protected properties.
Expanding training sets with both theoretical and measured data could reduce the risk that novel phases remain undetected.

Load-bearing premise

Symmetry-aware machine learning models trained on existing datasets will generalize accurately to unexplored regions of chemical space without systematic errors or missing novel phases outside the training distribution.

What would settle it

Targeted synthesis and measurement of several compounds flagged by the AI models that finds none of the predicted d-wave or g-wave altermagnetic order, or that the models fail to recover well-documented altermagnets already in the literature.

Figures

Figures reproduced from arXiv: 2604.15985 by Hosein Alavi-Rad, Mahyar Hassani-Vasmejani, Meysam Bagheri Tagani.

**Figure 3.** Figure 3: The high-throughput computational workflow employed for the discovery of magnetic topological materials. Starting from experimental magnetic structures in the MAGNDATA database, the pipeline utilizes [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗

**Figure 4.** Figure 4: Visualization of the Topogivity heuristic across the periodic table. The heatmap illustrates the machine-learned tendency of chemical elements to form topological bands, as [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗

read the original abstract

The landscape of condensed matter physics is facing an unprecedented data surge driven by high-throughput ab initio workflows and rapidly expanding experimental datasets. Traditional first-principles methods such as Density Functional Theory (DFT), despite their foundational role, suffer from cubic scaling, creating a major bottleneck when exploring the vast chemical space of quantum materials. This review analyzes how Machine Learning (ML) and Deep Learning (DL) are overcoming these limitations and accelerating the discovery of exotic phases of matter. We examine the shift from rigid descriptor-based models to flexible, symmetry-aware architectures, particularly E(3)-equivariant Graph Neural Networks (GNNs) that respect rotational and translational invariance. A central focus is the automated identification of topological phases, where ML models exploit symmetry indicators and elementary band representations to diagnose non-trivial topology without costly band structure integrations. The discussion culminates in a case study of the Altermagnet, a recently identified third class of magnetism beyond the ferromagnetic, antiferromagnetic dichotomy. We highlight how specialized AI search engines, combining graph theory with crystallographic symmetry analysis, have uncovered d-wave, g-wave, and even i-wave altermagnets, expanding the known landscape of magnetic order. The review concludes by addressing the interpretability gap and advocates for symbolic regression and active-learning frameworks to connect black-box predictions with experimentally verifiable mechanisms.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a review that surveys ML for quantum materials with a focus on symmetry-aware models and altermagnets, but it reports no new results or validations of its own.

read the letter

This review pulls together how machine learning is being applied to quantum materials, centering on symmetry and topology while highlighting altermagnets as an emerging class of magnetic order. It covers the shift from older descriptor-based approaches to E(3)-equivariant graph neural networks that build in rotational and translational invariance, and it notes how these can flag topological phases via symmetry indicators without full band integrations each time. That framing is clear and organizes the literature in a way that could help readers see the practical gains over traditional DFT scaling issues. The altermagnet section summarizes work where graph-theory plus crystallographic AI tools have turned up d-wave, g-wave, and i-wave examples, which expands the picture of possible magnetic orders beyond ferro- and antiferromagnets. The closing remarks on the interpretability gap and the need for symbolic regression or active learning are reasonable pointers for future work. The paper stays descriptive throughout and does not introduce new methods, datasets, or quantitative checks. Claims about AI uncovering new altermagnet phases rest entirely on the cited studies, with no held-out performance numbers, out-of-distribution tests, or direct comparisons to exhaustive scans provided here. That leaves the generalization strength of those models unexamined in this text itself. The discussion of limitations is light and does not dig into how training distributions might miss rare or higher-order phases. This paper is mainly for condensed-matter researchers who want a compact map of current ML uses in the area or a quick entry point on altermagnets. It is not aimed at readers seeking original algorithms or reproducible benchmarks. I would send it for peer review in a venue that publishes reviews or perspective pieces, since the synthesis is coherent and the topic is current, even though any strong claims about discovery power need to be traced back to the referenced papers rather than taken as established here.

Referee Report

1 major / 1 minor

Summary. The manuscript is a review article surveying the use of machine learning and deep learning to accelerate discovery in quantum materials. It contrasts the cubic scaling of DFT with data-driven approaches, describes the shift to symmetry-aware models such as E(3)-equivariant graph neural networks for topological classification via symmetry indicators and band representations, and devotes a case study to altermagnets, claiming that graph-theory-plus-crystallographic-symmetry AI engines have identified d-wave, g-wave, and i-wave realizations that expand the known taxonomy of magnetic order. The review closes by noting the interpretability challenge and advocating symbolic regression together with active learning.

Significance. If the cited ML-driven discoveries of higher-order altermagnets are reproducible and the symmetry-aware architectures generalize reliably, the review would usefully synthesize an emerging intersection of AI and condensed-matter physics, highlighting concrete routes by which data-driven methods can bypass traditional computational bottlenecks while respecting physical symmetries.

major comments (1)

[Abstract] Abstract (altermagnet case study): the central claim that specialized AI search engines have uncovered d-wave, g-wave, and i-wave altermagnets rests on the unverified extrapolation of symmetry-aware models (E(3)-equivariant GNNs or symmetry-indicator classifiers) beyond their training distributions. No precision-recall figures, out-of-distribution detection rates, or head-to-head comparisons against exhaustive DFT scans are referenced, leaving open the possibility that higher-order or rare phases are systematically missed or misclassified.

minor comments (1)

The transition from rigid descriptor-based models to flexible, symmetry-aware architectures would be clearer if accompanied by a brief concrete example (e.g., a specific GNN layer or symmetry-indicator workflow) rather than remaining at the level of general description.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their careful reading of the manuscript and for highlighting the need to strengthen the presentation of the altermagnet case study. We address the concern point by point below and have revised the abstract and relevant sections to incorporate additional context from the cited literature.

read point-by-point responses

Referee: [Abstract] Abstract (altermagnet case study): the central claim that specialized AI search engines have uncovered d-wave, g-wave, and i-wave altermagnets rests on the unverified extrapolation of symmetry-aware models (E(3)-equivariant GNNs or symmetry-indicator classifiers) beyond their training distributions. No precision-recall figures, out-of-distribution detection rates, or head-to-head comparisons against exhaustive DFT scans are referenced, leaving open the possibility that higher-order or rare phases are systematically missed or misclassified.

Authors: As a review article, the manuscript summarizes published results rather than presenting new model evaluations. The cited works on graph-theory and crystallographic-symmetry AI engines for altermagnets report precision-recall metrics on held-out test sets of known magnetic structures, along with explicit out-of-distribution tests on crystal families absent from training data; these benchmarks are referenced in the expanded case-study section. Head-to-head exhaustive DFT scans are not feasible for the full chemical space, which is precisely the computational bottleneck the review addresses; instead, the original studies validate candidate higher-order altermagnets through targeted DFT follow-up and symmetry-indicator consistency checks. We acknowledge that the original abstract was too concise and have revised it to state that the d-, g-, and i-wave realizations are literature-reported predictions supported by the performance figures and generalization tests in the referenced papers. A new paragraph in the case study now discusses reported false-positive rates and the subsequent experimental or computational confirmations, thereby clarifying the scope of extrapolation. revision: yes

Circularity Check

0 steps flagged

No circularity: review paper with descriptive claims only

full rationale

This is a review article summarizing ML/DL applications in quantum materials and altermagnets. It contains no original derivations, equations, fitted parameters, or predictions. Claims about AI uncovering d/g/i-wave altermagnets refer to external prior work via graph-theory and symmetry analysis, without self-citations or self-definitional reductions that load-bear the narrative. The text is purely expository and does not reduce any result to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a review article the manuscript introduces no new free parameters, axioms, or invented entities; all concepts discussed (E(3)-equivariant GNNs, symmetry indicators, altermagnets) are drawn from the existing literature.

pith-pipeline@v0.9.0 · 5553 in / 1202 out tokens · 64863 ms · 2026-05-10T08:02:46.352590+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

107 extracted references · 98 canonical work pages

[1]

The central role of density functional theory in the AI age,

B. Huang, G. F. von Rudorff, and O. A. von Lilienfeld, "The central role of density functional theory in the AI age," Science, vol. 381, pp. 170-175, 2023. https://doi.org/10.1126/science.abn3445

work page doi:10.1126/science.abn3445 2023
[2]

DFT techniques for resolution of significant practical materials problems,

J. A. Alarco and I. D. R. Mackinnon, "DFT techniques for resolution of significant practical materials problems," Journal of Physics: Conference Series, vol. 2678, p. 012005, 2023/12/01 2023. 10.1088/1742-6596/2678/1/012005

work page doi:10.1088/1742-6596/2678/1/012005 2023
[3]

A high-throughput and data- driven computational framework for novel quantum materials,

S. M. Kastuar, C. Rzepa, S. Rangarajan, and C. E. Ekuma, "A high-throughput and data- driven computational framework for novel quantum materials," APL Machine Learning, vol. 2, p. 046108, 2024. 10.1063/5.0221823

work page doi:10.1063/5.0221823 2024
[4]

Seitz, M

T. Ko, X. Li, and C. Wang, "Ground-State Energy and Related Properties Estimation in Quantum Chemistry with Linear Dependence on the Number of Atoms," in 2024 IEEE International Conference on Quantum Computing and Engineering (QCE), 2024, pp. 669-680. 10.1109/QCE60285.2024.00084

work page doi:10.1109/qce60285.2024.00084 2024
[5]

Toward improved property prediction of 2D materials using many-body quantum Monte Carlo methods,

D. Wines, J. Ahn, A. Benali, P. R. C. Kent, J. T. Krogel, Y. Kwon, et al., "Toward improved property prediction of 2D materials using many-body quantum Monte Carlo methods," Applied Physics Reviews, vol. 12, p. 031317, 2025. 10.1063/5.0220257

work page doi:10.1063/5.0220257 2025
[6]

Visualization, Exploration, and Screening of Chemical Space in Drug Discovery,

J. J. Naveja, F. I. Saldívar-González, D. L. Prado-Romero, A. J. Ruiz-Moreno, M. Velasco-Velázquez, R. A. Miranda-Quintana, et al., "Visualization, Exploration, and Screening of Chemical Space in Drug Discovery," in Computational Drug Discovery, ed, 2024, pp. 365-393. https://doi.org/10.1002/9783527840748.ch16

work page doi:10.1002/9783527840748.ch16 2024
[7]

High-throughput computational screening of nanoporous materials in targeted applications,

E. Ren, P. Guilbaud, and F.-X. Coudert, "High-throughput computational screening of nanoporous materials in targeted applications," Digital Discovery, vol. 1, pp. 355-374,
[8]

https://doi.org/10.1039/D2DD00018K

work page doi:10.1039/d2dd00018k
[9]

Leveraging State-of-the-Art Engines for Large-Scale Data Analysis in High Energy Physics,

V. E. Padulano, I. D. Kabadzhov, E. Tejedor Saavedra, E. Guiraud, and P. Alonso- Jordá, "Leveraging State-of-the-Art Engines for Large-Scale Data Analysis in High Energy Physics," Journal of Grid Computing, vol. 21, p. 9, 2023/02/10 2023. 10.1007/s10723-023-09645-2

work page doi:10.1007/s10723-023-09645-2 2023
[10]

PanDA: Production and Distributed Analysis System,

T. Maeno, A. Alekseev, F. H. Barreiro Megino, K. De, W. Guan, E. Karavakis, et al., "PanDA: Production and Distributed Analysis System," Computing and Software for Big Science, vol. 8, p. 4, 2024/01/23 2024. 10.1007/s41781-024-00114-3

work page doi:10.1007/s41781-024-00114-3 2024
[11]

Ab Initio Simulations and Materials Chemistry in the Age of Big Data,

G. R. Schleder, A. C. M. Padilha, A. Reily Rocha, G. M. Dalpian, and A. Fazzio, "Ab Initio Simulations and Materials Chemistry in the Age of Big Data," Journal of Chemical Information and Modeling, vol. 60, pp. 452-459, 2020/02/24 2020. 10.1021/acs.jcim.9b00781

work page doi:10.1021/acs.jcim.9b00781 2020
[12]

AI-accelerated materials informatics method for the discovery of ductile alloys,

I. Novikov, O. Kovalyova, A. Shapeev, and M. Hodapp, "AI-accelerated materials informatics method for the discovery of ductile alloys," Journal of Materials Research, vol. 37, pp. 3491-3504, 2022/11/01 2022. 10.1557/s43578-022-00783-z

work page doi:10.1557/s43578-022-00783-z 2022
[13]

A deep learning framework to emulate density functional theory,

B. G. del Rio, B. Phan, and R. Ramprasad, "A deep learning framework to emulate density functional theory," npj Computational Materials, vol. 9, p. 158, 2023/08/29 2023. 10.1038/s41524-023-01115-3

work page doi:10.1038/s41524-023-01115-3 2023
[14]

Quantum Machine Learning in Materials Prediction: A Case Study on ABO3 Perovskite Structures,

M. Naseri, S. Gusarov, and D. R. Salahub, "Quantum Machine Learning in Materials Prediction: A Case Study on ABO3 Perovskite Structures," The Journal of Physical Chemistry Letters, vol. 14, pp. 6940-6947, 2023/08/10 2023. 10.1021/acs.jpclett.3c01703

work page doi:10.1021/acs.jpclett.3c01703 2023
[15]

Electronic excited states from physically constrained machine learning,

E. Cignoni, D. Suman, J. Nigam, L. Cupellini, B. Mennucci, and M. Ceriotti, "Electronic excited states from physically constrained machine learning," ACS Central Science, vol. 10, pp. 637-648, 2024. https://doi.org/10.1021/acscentsci.3c01480

work page doi:10.1021/acscentsci.3c01480 2024
[16]

A perspective on machine learning and data science for strongly correlated electron problems,

S. Johnston, E. Khatami, and R. Scalettar, "A perspective on machine learning and data science for strongly correlated electron problems," Carbon Trends, vol. 9, p. 100231, 2022/10/01/ 2022. https://doi.org/10.1016/j.cartre.2022.100231

work page doi:10.1016/j.cartre.2022.100231 2022
[17]

Integration of Quantum Computing with Artificial Intelligence: A Systematic Review,

A. Sharma and Z. Ali, "Integration of Quantum Computing with Artificial Intelligence: A Systematic Review," Journal of Engineering Research and Reports, vol. 27, pp. 329- 343, 2025. https://doi.org/10.9734/jerr/2025/v27i91644

work page doi:10.9734/jerr/2025/v27i91644 2025
[18]

R., & Origlia, L

J. McGreevy, "Generalized Symmetries in Condensed Matter," Annual Review of Condensed Matter Physics, vol. 14, pp. 57-82, 2023. https://doi.org/10.1146/annurev- conmatphys-040721-021029

work page doi:10.1146/annurev- 2023
[19]

Topological Materials for Functional Optoelectronic Devices,

H. Chorsi, B. Cheng, B. Zhao, J. Toudert, V. Asadchy, O. F. Shoron, et al., "Topological Materials for Functional Optoelectronic Devices," Advanced Functional Materials, vol. 32, p. 2110655, 2022. https://doi.org/10.1002/adfm.202110655

work page doi:10.1002/adfm.202110655 2022
[20]

Axion insulators protected by ${C}_{2}\mathbb{T}$ symmetry, their $K$-theory invariants, and material realizations,

R. González-Hernández, C. Pinilla, and B. Uribe, "Axion insulators protected by ${C}_{2}\mathbb{T}$ symmetry, their $K$-theory invariants, and material realizations," Physical Review B, vol. 106, p. 195144, 11/23/ 2022. 10.1103/PhysRevB.106.195144

work page doi:10.1103/physrevb.106.195144 2022
[21]

Topological materials discovery from crystal symmetry,

B. J. Wieder, B. Bradlyn, J. Cano, Z. Wang, M. G. Vergniory, L. Elcoro, et al., "Topological materials discovery from crystal symmetry," Nature Reviews Materials, vol. 7, pp. 196-216, 2022/03/01 2022. 10.1038/s41578-021-00380-2

work page doi:10.1038/s41578-021-00380-2 2022
[22]

All topological bands of all nonmagnetic stoichiometric materials,

M. G. Vergniory, B. J. Wieder, L. Elcoro, S. S. P. Parkin, C. Felser, B. A. Bernevig, et al., "All topological bands of all nonmagnetic stoichiometric materials," Science, vol. 376, p. eabg9094, 2022. doi:10.1126/science.abg9094

work page doi:10.1126/science.abg9094 2022
[23]

High- throughput calculations of magnetic topological materials,

Y. Xu, L. Elcoro, Z.-D. Song, B. J. Wieder, M. G. Vergniory, N. Regnault, et al., "High- throughput calculations of magnetic topological materials," Nature, vol. 586, pp. 702-707, 2020/10/01 2020. 10.1038/s41586-020-2837-0

work page doi:10.1038/s41586-020-2837-0 2020
[24]

High-throughput search for magnetic and topological order in transition metal oxides,

N. C. Frey, M. K. Horton, J. M. Munro, S. M. Griffin, K. A. Persson, and V. B. Shenoy, "High-throughput search for magnetic and topological order in transition metal oxides," Science Advances, vol. 6, p. eabd1076, 2020. doi:10.1126/sciadv.abd1076

work page doi:10.1126/sciadv.abd1076 2020
[25]

Tamang, S

R. Tamang, S. Gurung, D. P. Rai, S. Brahimi, and S. Lounis. (2025, Altermagnetism and Altermagnets: A Brief Review. Magnetism 5(3), 17. 10.3390/magnetism5030017

work page doi:10.3390/magnetism5030017 2025
[26]

Revealing the Hidden Spin-Polarized Bands in a Superconducting Tl Bilayer Crystal,

T. Kobayashi, Y. Toichi, K. Yaji, Y. Nakata, Y. Yaoita, M. Iwaoka, et al., "Revealing the Hidden Spin-Polarized Bands in a Superconducting Tl Bilayer Crystal," Nano Letters, vol. 23, pp. 7675-7682, 2023/08/23 2023. 10.1021/acs.nanolett.3c02387

work page doi:10.1021/acs.nanolett.3c02387 2023
[27]

Compensated Ferrimagnets with Colossal Spin Splitting in Organic Compounds,

T. Kawamura, K. Yoshimi, K. Hashimoto, A. Kobayashi, and T. Misawa, "Compensated Ferrimagnets with Colossal Spin Splitting in Organic Compounds," Physical Review Letters, vol. 132, p. 156502, 04/10/ 2024. 10.1103/PhysRevLett.132.156502

work page doi:10.1103/physrevlett.132.156502 2024
[29]

Symmetry-adapted modeling for molecules and crystals,

H. Kusunose, R. Oiwa, and S. Hayami, "Symmetry-adapted modeling for molecules and crystals," Physical Review B, vol. 107, p. 195118, 05/11/ 2023. 10.1103/PhysRevB.107.195118

work page doi:10.1103/physrevb.107.195118 2023
[30]

Representation of materials by kernel mean embedding,

M. Kusaba, Y. Hayashi, C. Liu, A. Wakiuchi, and R. Yoshida, "Representation of materials by kernel mean embedding," Physical Review B, vol. 108, p. 134107, 10/16/
[31]

10.1103/PhysRevB.108.134107

work page doi:10.1103/physrevb.108.134107
[32]

Can One Hear the Shape of a Molecule (from its Coulomb Matrix Eigenvalues)?,

J. Schrier, "Can One Hear the Shape of a Molecule (from its Coulomb Matrix Eigenvalues)?," Journal of Chemical Information and Modeling, vol. 60, pp. 3804-3811, 2020/08/24 2020. 10.1021/acs.jcim.0c00631

work page doi:10.1021/acs.jcim.0c00631 2020
[33]

DScribe: Library of descriptors for machine learning in materials science,

L. Himanen, M. O. J. Jäger, E. V. Morooka, F. Federici Canova, Y. S. Ranawat, D. Z. Gao, et al., "DScribe: Library of descriptors for machine learning in materials science," Computer Physics Communications, vol. 247, p. 106949, 2020/02/01/ 2020. https://doi.org/10.1016/j.cpc.2019.106949

work page doi:10.1016/j.cpc.2019.106949 2020
[34]

Gorsse, C

T. Lam Pham, H. Kino, K. Terakura, T. Miyake, K. Tsuda, I. Takigawa, et al., "Machine learning reveals orbital interaction in materials," Sci Technol Adv Mater, vol. 18, pp. 756- 765, 2017. 10.1080/14686996.2017.1378060

work page doi:10.1080/14686996.2017.1378060 2017
[35]

Extraction of Local Structure Information from X-ray Absorption Near-Edge Structure: A Machine Learning Approach,

M. Higashi and H. Ikeno, "Extraction of Local Structure Information from X-ray Absorption Near-Edge Structure: A Machine Learning Approach," MATERIALS TRANSACTIONS, vol. 64, pp. 2179-2184, 2023. 10.2320/matertrans.MT-MG2022028

work page doi:10.2320/matertrans.mt-mg2022028 2023
[36]

E(n)-Equivariant cartesian tensor message passing interatomic potential,

J. Wang, Y. Wang, H. Zhang, Z. Yang, Z. Liang, J. Shi, et al., "E(n)-Equivariant cartesian tensor message passing interatomic potential," Nature Communications, vol. 15, p. 7607, 2024/09/01 2024. 10.1038/s41467-024-51886-6

work page doi:10.1038/s41467-024-51886-6 2024
[37]

Physics-Inspired Structural Representations for Molecules and Materials,

F. Musil, A. Grisafi, A. P. Bartók, C. Ortner, G. Csányi, and M. Ceriotti, "Physics-Inspired Structural Representations for Molecules and Materials," Chemical Reviews, vol. 121, pp. 9759-9815, 2021/08/25 2021. 10.1021/acs.chemrev.1c00021

work page doi:10.1021/acs.chemrev.1c00021 2021
[38]

Hao Zhang, Tingting Wu, Siyao Cheng, and Jie Liu

S. Georgousis, M. P. Kenning, and X. Xie, "Graph Deep Learning: State of the Art and Challenges," IEEE Access, vol. 9, pp. 22106-22140, 2021. 10.1109/ACCESS.2021.3055280

work page doi:10.1109/access.2021.3055280 2021
[39]

Kirstein, L

T. Kirstein, L. Petrich, R. R. Purushottam Raj Purohit, J.-S. Micha, and V. Schmidt. (2023, CNN-Based Laue Spot Morphology Predictor for Reliable Crystallographic Descriptor Estimation. Materials 16(9), 3397. 10.3390/ma16093397

work page doi:10.3390/ma16093397 2023
[40]

Real-Space DMRG,

"Real-Space DMRG," in Density Matrix and Tensor Network Renormalization, T. Xiang, Ed., ed Cambridge: Cambridge University Press, 2023, pp. 103-122. DOI: 10.1017/9781009398671.008

work page doi:10.1017/9781009398671.008 2023
[41]

Qubism: self-similar visualization of many-body wavefunctions,

J. Rodríguez-Laguna, P. Migdał, M. I. Berganza, M. Lewenstein, and G. Sierra, "Qubism: self-similar visualization of many-body wavefunctions," New Journal of Physics, vol. 14, p. 053028, 2012/05/22 2012. 10.1088/1367-2630/14/5/053028

work page doi:10.1088/1367-2630/14/5/053028 2012
[42]

Quantum convolutional neural network for phase recognition in two dimensions,

L. C. Sander, N. A. McMahon, P. Zapletal, and M. J. Hartmann, "Quantum convolutional neural network for phase recognition in two dimensions," Physical Review Research, vol. 7, p. L042032, 11/07/ 2025. 10.1103/vpyw-nszk

work page doi:10.1103/vpyw-nszk 2025
[43]

doi: 10.1038/s43246-022-00315-6

P. Reiser, M. Neubert, A. Eberhard, L. Torresi, C. Zhou, C. Shao, et al., "Graph neural networks for materials science and chemistry," Communications Materials, vol. 3, p. 93, 2022/11/26 2022. 10.1038/s43246-022-00315-6

work page doi:10.1038/s43246-022-00315-6 2022
[44]

E(n) Equivariant Graph Neural Networks,

V. c. G. Satorras, E. Hoogeboom, and M. Welling, "E(n) Equivariant Graph Neural Networks," presented at the Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2021

2021
[45]

A simple approach to rotationally invariant machine learning of a vector quantity,

J. Martinka, M. Pederzoli, M. Barbatti, P. O. Dral, and J. Pittner, "A simple approach to rotationally invariant machine learning of a vector quantity," The Journal of Chemical Physics, vol. 161, p. 174104, 2024. 10.1063/5.0230176

work page doi:10.1063/5.0230176 2024
[46]

E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction,

R. Roche, B. Moussad, M. H. Shuvo, and D. Bhattacharya, "E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction," PLOS Computational Biology, vol. 19, p. e1011435, 2023. 10.1371/journal.pcbi.1011435

work page doi:10.1371/journal.pcbi.1011435 2023
[47]

Addressing fairness in artificial intelligence for medical imaging.Nature Communications, 13:4581, 2022

S. Batzner, A. Musaelian, L. Sun, M. Geiger, J. P. Mailoa, M. Kornbluth, et al., "E(3)- equivariant graph neural networks for data-efficient and accurate interatomic potentials," Nature Communications, vol. 13, p. 2453, 2022/05/04 2022. 10.1038/s41467-022- 29939-5

work page doi:10.1038/s41467-022- 2022
[48]

FAENet: Frame Averaging Equivariant GNN for Materials Modeling,

A. A. Duval, V. Schmidt, A. Hernández-Garcı́a, S. Miret, F. D. Malliaros, Y. Bengio, et al., "FAENet: Frame Averaging Equivariant GNN for Materials Modeling," presented at the Proceedings of the 40th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2023

2023
[49]

Higher-order equivariant neural networks for charge density prediction in materials,

T. Koker, K. Quigley, E. Taw, K. Tibbetts, and L. Li, "Higher-order equivariant neural networks for charge density prediction in materials," npj Computational Materials, vol. 10, p. 161, 2024/07/26 2024. 10.1038/s41524-024-01343-1

work page doi:10.1038/s41524-024-01343-1 2024
[50]

A critical review of machine learning interatomic potentials and hamiltonian

L. Yifan, Z. Xiuying, L. Mingkang, and S. Lei, "A critical review of machine learning interatomic potentials and Hamiltonian," Journal of Surveillance, Security and Safety, vol. 5, p. 43, 2025. 10.20517/jmi.2025.17

work page doi:10.20517/jmi.2025.17 2025
[51]

Spin-dependent graph neural network potential for magnetic materials,

H. Yu, Y. Zhong, L. Hong, C. Xu, W. Ren, X. Gong, et al., "Spin-dependent graph neural network potential for magnetic materials," Physical Review B, vol. 109, p. 144426, 04/26/
[52]

10.1103/PhysRevB.109.144426

work page doi:10.1103/physrevb.109.144426
[53]

Towards harmonization of SO(3)-equivariance and expressiveness: a hybrid deep learning framework for electronic-structure Hamiltonian prediction,

S. Yin, X. Pan, X. Zhu, T. Gao, H. Zhang, F. Wu, et al., "Towards harmonization of SO(3)-equivariance and expressiveness: a hybrid deep learning framework for electronic-structure Hamiltonian prediction," Machine Learning: Science and Technology, vol. 5, p. 045038, 2024/11/12 2024. 10.1088/2632-2153/ad8d30

work page doi:10.1088/2632-2153/ad8d30 2024
[54]

Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation,

H. Li, Z. Wang, N. Zou, M. Ye, R. Xu, X. Gong, et al., "Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation," Nature Computational Science, vol. 2, pp. 367-377, 2022/06/01 2022. 10.1038/s43588-022- 00265-6

work page doi:10.1038/s43588-022- 2022
[55]

Efficient determination of the Hamiltonian and electronic properties using graph neural network with complete local coordinates,

M. Su, J.-H. Yang, H.-J. Xiang, and X.-G. Gong, "Efficient determination of the Hamiltonian and electronic properties using graph neural network with complete local coordinates," Machine Learning: Science and Technology, vol. 4, p. 035010, 2023/07/24

2023
[56]

10.1088/2632-2153/accb26

work page doi:10.1088/2632-2153/accb26
[57]

Direct Prediction of Phonon Density of States With Euclidean Neural Networks,

Z. Chen, N. Andrejevic, T. Smidt, Z. Ding, Q. Xu, Y.-T. Chi, et al., "Direct Prediction of Phonon Density of States With Euclidean Neural Networks," Advanced Science, vol. 8, p. 2004214, 2021/06/01 2021. https://doi.org/10.1002/advs.202004214

work page doi:10.1002/advs.202004214 2021
[58]

Physically Informed Machine Learning Prediction of Electronic Density of States,

V. Fung, P. Ganesh, and B. G. Sumpter, "Physically Informed Machine Learning Prediction of Electronic Density of States," Chemistry of Materials, vol. 34, pp. 4848- 4855, 2022/06/14 2022. 10.1021/acs.chemmater.1c04252

work page doi:10.1021/acs.chemmater.1c04252 2022
[59]

Machine learning the local electronic density of states,

A. Aryanpour and A. Sadeghi, "Machine learning the local electronic density of states," Physical Review B, vol. 112, p. 115101, 09/02/ 2025. 10.1103/91sg-6ydl

work page doi:10.1103/91sg-6ydl 2025
[60]

Strong coupling of hybrid states of light and matter in cavity-coupled quantum dot solids,

A. Sangeetha, K. Reivanth, T. Thrupthika, S. Ramya, and D. Nataraj, "Strong coupling of hybrid states of light and matter in cavity-coupled quantum dot solids," Scientific Reports, vol. 13, p. 16662, 2023. https://doi.org/10.1038/s41598-023-42105-1

work page doi:10.1038/s41598-023-42105-1 2023
[61]

Machine Learning Topological Invariants with Neural Networks,

P. Zhang, H. Shen, and H. Zhai, "Machine Learning Topological Invariants with Neural Networks," Physical Review Letters, vol. 120, p. 066401, 02/06/ 2018. 10.1103/PhysRevLett.120.066401

work page doi:10.1103/physrevlett.120.066401 2018
[62]

Deep learning topological invariants of band insulators,

N. Sun, J. Yi, P. Zhang, H. Shen, and H. Zhai, "Deep learning topological invariants of band insulators," Physical Review B, vol. 98, p. 085402, 08/02/ 2018. 10.1103/PhysRevB.98.085402

work page doi:10.1103/physrevb.98.085402 2018
[63]

Unsupervised learning of topological phase diagram using topological data analysis,

S. Park, Y. Hwang, and B.-J. Yang, "Unsupervised learning of topological phase diagram using topological data analysis," Physical Review B, vol. 105, p. 195115, 05/10/ 2022. 10.1103/PhysRevB.105.195115

work page doi:10.1103/physrevb.105.195115 2022
[64]

Detection of topological materials with machine learning,

N. Claussen, B. A. Bernevig, and N. Regnault, "Detection of topological materials with machine learning," Physical Review B, vol. 101, p. 245117, 06/03/ 2020. 10.1103/PhysRevB.101.245117

work page doi:10.1103/physrevb.101.245117 2020
[65]

Identifying crystal structures beyond known prototypes from x-ray powder diffraction spectra,

A. S. Parackal, R. E. A. Goodall, F. A. Faber, and R. Armiento, "Identifying crystal structures beyond known prototypes from x-ray powder diffraction spectra," Physical Review Materials, vol. 8, p. 103801, 10/02/ 2024. 10.1103/PhysRevMaterials.8.103801

work page doi:10.1103/physrevmaterials.8.103801 2024
[66]

New magnetic topological materials from high-throughput search,

I. Robredo, Y. Xu, Y. Jiang, C. Felser, B. A. Bernevig, L. Elcoro, et al., "New magnetic topological materials from high-throughput search," Science Advances, vol. 11, p. eadv8780. 10.1126/sciadv.adv8780

work page doi:10.1126/sciadv.adv8780
[67]

Discovering two-dimensional magnetic topological insulators by machine learning,

H. Xu, Y. Jiang, H. Wang, and J. Wang, "Discovering two-dimensional magnetic topological insulators by machine learning," Physical Review B, vol. 109, p. 035122, 01/11/ 2024. 10.1103/PhysRevB.109.035122

work page doi:10.1103/physrevb.109.035122 2024
[68]

QuTiP- BoFiN: A bosonic and fermionic numerical hierarchical-equations-of-motion library with applications in light-harvesting, quantum control, and single-molecule electronics,

N. Lambert, T. Raheja, S. Cross, P. Menczel, S. Ahmed, A. Pitchford, et al., "QuTiP- BoFiN: A bosonic and fermionic numerical hierarchical-equations-of-motion library with applications in light-harvesting, quantum control, and single-molecule electronics," Physical Review Research, vol. 5, p. 013181, 03/15/ 2023. 10.1103/PhysRevResearch.5.013181

work page doi:10.1103/physrevresearch.5.013181 2023
[69]

Three-dimensional photonic topological insulator without spin–orbit coupling,

M. Kim, Z. Wang, Y. Yang, H. T. Teo, J. Rho, and B. Zhang, "Three-dimensional photonic topological insulator without spin–orbit coupling," Nature Communications, vol. 13, p. 3499, 2022/06/17 2022. 10.1038/s41467-022-30909-0

work page doi:10.1038/s41467-022-30909-0 2022
[70]

Enhancing Adjoint Optimization-Based Photonic Inverse Design with Explainable Machine Learning,

C. Yeung, D. Ho, B. Pham, K. T. Fountaine, Z. Zhang, K. Levy, et al., "Enhancing Adjoint Optimization-Based Photonic Inverse Design with Explainable Machine Learning," ACS Photonics, vol. 9, pp. 1577-1585, 2022/05/18 2022. 10.1021/acsphotonics.1c01636

work page doi:10.1021/acsphotonics.1c01636 2022
[71]

Deep-learning-based inverse design of phononic crystals for anticipated wave attenuation,

S. Han, Q. Han, and C. Li, "Deep-learning-based inverse design of phononic crystals for anticipated wave attenuation," Journal of Applied Physics, vol. 132, p. 154901, 2022. 10.1063/5.0111182

work page doi:10.1063/5.0111182 2022
[72]

Unsupervised learning of interacting topological phases from experimental observables,

L.-W. Yu, S.-Y. Zhang, P.-X. Shen, and D.-L. Deng, "Unsupervised learning of interacting topological phases from experimental observables," Fundamental Research, vol. 4, pp. 1086-1091, 2024/09/01/ 2024. https://doi.org/10.1016/j.fmre.2022.12.016

work page doi:10.1016/j.fmre.2022.12.016 2024
[73]

Supervised and unsupervised learning of the many-body critical phase, phase transitions, and critical exponents in disordered quantum systems,

A. Ahmed and N. Roy, "Supervised and unsupervised learning of the many-body critical phase, phase transitions, and critical exponents in disordered quantum systems," Physical Review B, vol. 111, p. 195151, 05/22/ 2025. 10.1103/PhysRevB.111.195151

work page doi:10.1103/physrevb.111.195151 2025
[74]

Unsupervised machine learning for detecting mutual independence among eigenstate regimes in interacting quasiperiodic chains,

C. Beveridge, K. Hart, C. R. Cristani, X. Li, E. Barbierato, and Y.-T. Hsu, "Unsupervised machine learning for detecting mutual independence among eigenstate regimes in interacting quasiperiodic chains," Physical Review B, vol. 111, p. L140202, 04/25/ 2025. 10.1103/PhysRevB.111.L140202

work page doi:10.1103/physrevb.111.l140202 2025
[75]

Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions,

S. Tibaldi, G. Magnifico, D. Vodola, and E. Ercolessi, "Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions," SciPost Physics, vol. 14, p. 005, 2023. 10.21468/SciPostPhys.14.1.005

work page doi:10.21468/scipostphys.14.1.005 2023
[76]

ˇSmejkal, J

L. Šmejkal, J. Sinova, and T. Jungwirth, "Emerging Research Landscape of Altermagnetism," Physical Review X, vol. 12, p. 040501, 12/08/ 2022. 10.1103/PhysRevX.12.040501

work page doi:10.1103/physrevx.12.040501 2022
[77]

Crystal Chemistry and Design Principles of Altermagnets,

C.-C. Wei, E. Lawrence, A. Tran, and H. Ji, "Crystal Chemistry and Design Principles of Altermagnets," ACS Organic & Inorganic Au, vol. 4, pp. 604-619, 2024/12/04 2024. 10.1021/acsorginorgau.4c00064

work page doi:10.1021/acsorginorgau.4c00064 2024
[78]

Magnetization reversal through an antiferromagnetic state,

S. Ghara, E. Barts, K. Vasin, D. Kamenskyi, L. Prodan, V. Tsurkan, et al., "Magnetization reversal through an antiferromagnetic state," Nature Communications, vol. 14, p. 5174, 2023/08/24 2023. 10.1038/s41467-023-40722-y

work page doi:10.1038/s41467-023-40722-y 2023
[79]

Altermagnetic Band Splitting in 10 nm Epitaxial CrSb Thin Films,

S. Santhosh, P. Corbae, W. J. Yánez-Parreño, S. Ghosh, C. J. Jensen, A. V. Fedorov, et al., "Altermagnetic Band Splitting in 10 nm Epitaxial CrSb Thin Films," Advanced Materials, vol. 37, p. e08977, 2025/11/01 2025. https://doi.org/10.1002/adma.202508977

work page doi:10.1002/adma.202508977 2025
[80]

Observation of plaid-like spin splitting in a noncoplanar antiferromagnet,

Y.-P. Zhu, X. Chen, X.-R. Liu, Y. Liu, P. Liu, H. Zha, et al., "Observation of plaid-like spin splitting in a noncoplanar antiferromagnet," Nature, vol. 626, pp. 523-528, 2024/02/01

2024
[81]

10.1038/s41586-024-07023-w

work page doi:10.1038/s41586-024-07023-w

Showing first 80 references.