{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T10:17:30Z","timestamp":1783333050536,"version":"3.54.6"},"reference-count":63,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"crossref","award":["RS-2025-25456722"],"award-info":[{"award-number":["RS-2025-25456722"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"crossref","award":["2019-0-00003"],"award-info":[{"award-number":["2019-0-00003"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2025-02309510"],"award-info":[{"award-number":["RS-2025-02309510"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"crossref","award":["RS-2024-00466693"],"award-info":[{"award-number":["RS-2024-00466693"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Determining the ground state of a many-body Hamiltonian is a central problem across physics, chemistry, and combinatorial optimization, yet it is often classically intractable due to the exponential growth of Hilbert space with system size. Even on fault-tolerant quantum computers, quantum algorithms with convergence guarantees\u2014such as quantum phase estimation and quantum subspace methods\u2014require an initial state with sufficiently large overlap with the true ground state to be effective. Variational quantum eigensolvers (VQEs) are natural candidates for preparing such states; however, standard VQEs typically exhibit poor generalization, requiring retraining for each Hamiltonian instance, and often suffer from barren plateaus, where gradients can vanish exponentially with circuit depth and system size. To address these limitations, we propose an end-to-end representation learning framework that combines a graph autoencoder with a classical neural network to generate VQE parameters that generalize across Hamiltonian instances. By encoding interaction topology and coupling structure, the proposed model produces high-overlap initial states without instance-specific optimization. Through extensive numerical experiments on families of one- and two-local Hamiltonians, we demonstrate improved generalization and trainability, manifested as reduced test error and a significantly milder decay of gradient variance. We further show that our method substantially accelerates convergence in quantum subspace-based eigensolvers, highlighting its practical impact for downstream quantum algorithms.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae7eee","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:55:17Z","timestamp":1781736917000},"page":"045007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving generalization and trainability of quantum eigensolvers via graph neural encoding"],"prefix":"10.1088","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4663-070X","authenticated-orcid":true,"given":"Jungyun","family":"Lee","sequence":"first","affiliation":[{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3177-4143","authenticated-orcid":true,"given":"Daniel K","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University"},{"name":"Yonsei University"},{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"mlstae7eeebib1","article-title":"Simulating physics with computers, international journal of theoretical physics","author":"Feynman","year":"1982","type":"other"},{"key":"mlstae7eeebib2","volume":"vol 6","author":"Levine","year":"2009","type":"book"},{"key":"mlstae7eeebib3","article-title":"A quantum approximate optimization algorithm","author":"Farhi","year":"2014","type":"preprint"},{"key":"mlstae7eeebib4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.3389\/fphy.2014.00005","type":"journal-article","article-title":"Ising formulations of many NP problems","volume":"2","author":"Lucas","year":"2014","journal-title":"Front. Phys."},{"key":"mlstae7eeebib5","doi-asserted-by":"publisher","first-page":"1952","DOI":"10.1038\/s41467-023-37587-6","type":"journal-article","article-title":"Evaluating the evidence for exponential quantum advantage in ground-state quantum chemistry","volume":"14","author":"Lee","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib6","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1126\/science.273.5278.1073","type":"journal-article","article-title":"universal quantum simulators","volume":"273","author":"Lloyd","year":"1996","journal-title":"Science"},{"key":"mlstae7eeebib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.120502","type":"journal-article","article-title":"Training variational quantum algorithms is NP-hard","volume":"127","author":"Bittel","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstae7eeebib8","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/nature23458","type":"journal-article","article-title":"Quantum computational supremacy","volume":"549","author":"Harrow","year":"2017","journal-title":"Nature"},{"key":"mlstae7eeebib9","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1038\/s41567-018-0124-x","type":"journal-article","article-title":"Characterizing quantum supremacy in near-term devices","volume":"14","author":"Boixo","year":"2018","journal-title":"Nat. Phys."},{"key":"mlstae7eeebib10","doi-asserted-by":"publisher","first-page":"191","DOI":"10.22331\/q-2019-10-07-191","type":"journal-article","article-title":"Theory of variational quantum simulation","volume":"3","author":"Yuan","year":"2019","journal-title":"Quantum"},{"key":"mlstae7eeebib11","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1090\/S0002-9939-1959-0108732-6","type":"journal-article","article-title":"On the product of semi-groups of operators","volume":"10","author":"Trotter","year":"1959","journal-title":"Proc. Am. Math. Soc."},{"key":"mlstae7eeebib12","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/0375-9601(93)90701-Z","type":"journal-article","article-title":"Improved trotter-like formula","volume":"180","author":"Suzuki","year":"1993","journal-title":"Phys. Lett. A"},{"key":"mlstae7eeebib13","article-title":"Quantum measurements and the Abelian stabilizer problem","author":"Kitaev","year":"1995","type":"preprint"},{"key":"mlstae7eeebib14","doi-asserted-by":"publisher","first-page":"5162","DOI":"10.1103\/PhysRevLett.83.5162","type":"journal-article","article-title":"Quantum algorithm providing exponential speed increase for finding eigenvalues and eigenvectors","volume":"83","author":"Abrams","year":"1999","journal-title":"Phys. Rev. Lett."},{"key":"mlstae7eeebib15","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1126\/science.1113479","type":"journal-article","article-title":"Simulated quantum computation of molecular energies","volume":"309","author":"Aspuru-Guzik","year":"2005","journal-title":"Science"},{"key":"mlstae7eeebib16","doi-asserted-by":"publisher","first-page":"79","DOI":"10.22331\/q-2018-08-06-79","type":"journal-article","article-title":"Quantum computing in the nisq era and beyond","volume":"2","author":"Preskill","year":"2018","journal-title":"Quantum"},{"key":"mlstae7eeebib17","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.2.030301","type":"journal-article","article-title":"Simulating many-body systems with a projective quantum eigensolver","volume":"2","author":"Stair","year":"2021","journal-title":"PRX quantum"},{"key":"mlstae7eeebib18","article-title":"A polynomial-time dissipation-based quantum algorithm for solving the ground states of a class of classically hard hamiltonians","author":"Shang","year":"2024","type":"preprint"},{"key":"mlstae7eeebib19","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.3.040305","type":"journal-article","article-title":"Ground-state preparation and energy estimation on early fault-tolerant quantum computers via quantum eigenvalue transformation of unitary matrices","volume":"3","author":"Dong","year":"2022","journal-title":"PRX quantum"},{"key":"mlstae7eeebib20","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1137\/21M145954X","type":"journal-article","article-title":"A theory of quantum subspace diagonalization","volume":"43","author":"Epperly","year":"2022","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"mlstae7eeebib21","doi-asserted-by":"publisher","first-page":"5014","DOI":"10.1038\/s41467-025-59716-z","type":"journal-article","article-title":"Krylov diagonalization of large many-body hamiltonians on a quantum processor","volume":"16","author":"Yoshioka","year":"2025","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib22","article-title":"Quantum-centric algorithm for sample-based krylov diagonalization","author":"Yu","year":"2025","type":"preprint"},{"key":"mlstae7eeebib23","doi-asserted-by":"publisher","first-page":"eadu9991","DOI":"10.1126\/sciadv.adu9991","type":"journal-article","article-title":"Chemistry beyond the scale of exact diagonalization on a quantum-centric supercomputer","volume":"11","author":"Robledo-Moreno","year":"2025","journal-title":"Sci. Adv."},{"key":"mlstae7eeebib24","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.1038\/ncomms5213","type":"journal-article","article-title":"A variational eigenvalue solver on a photonic quantum processor","volume":"5","author":"Peruzzo","year":"2014","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib25","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/2\/023023","type":"journal-article","article-title":"The theory of variational hybrid quantum-classical algorithms","volume":"18","author":"McClean","year":"2016","journal-title":"New J. Phys."},{"key":"mlstae7eeebib26","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s42254-021-00348-9","type":"journal-article","article-title":"Variational quantum algorithms","volume":"3","author":"Cerezo","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"mlstae7eeebib27","article-title":"Variational quantum algorithms for combinatorial optimization","author":"Perez Ramirez","year":"2024","type":"preprint"},{"key":"mlstae7eeebib28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2022.08.003","type":"journal-article","article-title":"The variational quantum eigensolver: a review of methods and best practices","volume":"986","author":"Tilly","year":"2022","journal-title":"Phys. Rep."},{"key":"mlstae7eeebib29","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ad17d8","type":"journal-article","article-title":"Variational quantum algorithms for simulation of lindblad dynamics","volume":"9","author":"Watad","year":"2024","journal-title":"Quantum Sci. Technol."},{"key":"mlstae7eeebib30","author":"Wittek","year":"2014","type":"book"},{"key":"mlstae7eeebib31","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab4eb5","type":"journal-article","article-title":"Parameterized quantum circuits as machine learning models","volume":"4","author":"Benedetti","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstae7eeebib32","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s42484-021-00061-x","type":"journal-article","article-title":"Quantum convolutional neural network for classical data classification","volume":"4","author":"Hur","year":"2022","journal-title":"Quantum Mach. Intell."},{"key":"mlstae7eeebib33","article-title":"Quantum-selected configuration interaction: classical diagonalization of hamiltonians in subspaces selected by quantum computers","author":"Kanno","year":"2023","type":"preprint"},{"key":"mlstae7eeebib34","article-title":"Myths around quantum computation before full fault tolerance: what no-go theorems rule out and what they don\u2019t","author":"Zimbor\u00e1s","year":"2025","type":"preprint"},{"key":"mlstae7eeebib35","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1038\/s41467-018-07090-4","type":"journal-article","article-title":"Barren plateaus in quantum neural network training landscapes","volume":"9","author":"McClean","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42254-025-00813-9","type":"journal-article","article-title":"Barren plateaus in variational quantum computing","volume":"7","author":"Larocca","year":"2025","journal-title":"Nat. Rev. Phys."},{"key":"mlstae7eeebib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.21.014053","type":"journal-article","article-title":"Neural-network-encoded variational quantum algorithms","volume":"21","author":"Miao","year":"2024","journal-title":"Phys. Rev. Appl."},{"key":"mlstae7eeebib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.032309","type":"journal-article","article-title":"Quantum circuit learning","volume":"98","author":"Mitarai","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstae7eeebib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.032331","type":"journal-article","article-title":"Evaluating analytic gradients on quantum hardware","volume":"99","author":"Schuld","year":"2019","journal-title":"Phys. Rev. A"},{"key":"mlstae7eeebib40","article-title":"Generalized Laplacian positional encoding for graph representation learning","author":"Maskey","year":"2022","type":"preprint"},{"key":"mlstae7eeebib41","article-title":"Graph neural networks with learnable structural and positional representations","author":"Dwivedi","year":"2022","type":"preprint"},{"key":"mlstae7eeebib42","first-page":"pp 253","type":"conference-proceedings","article-title":"Egat: Edge-featured graph attention network","volume":"vol 30","author":"Wang","year":"2021"},{"key":"mlstae7eeebib43","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2023\/752","type":"preprint","article-title":"Graph pooling for graph neural networks: Progress, challenges, and opportunities","author":"Liu","year":"2023"},{"key":"mlstae7eeebib44","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s10462-024-10949-2","type":"journal-article","article-title":"Graph pooling for graph-level representation learning: a survey","volume":"58","author":"Li","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"mlstae7eeebib45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106790","type":"journal-article","article-title":"Graph explicit pooling for graph-level representation learning","volume":"181","author":"Liu","year":"2025","journal-title":"Neural Netw."},{"key":"mlstae7eeebib46","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1038\/nature23879","type":"journal-article","article-title":"Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets","volume":"549","author":"Kandala","year":"2017","journal-title":"Nature"},{"key":"mlstae7eeebib47","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41586-023-06096-3","type":"journal-article","article-title":"Evidence for the utility of quantum computing before fault tolerance","volume":"618","author":"Kim","year":"2023","journal-title":"Nature"},{"key":"mlstae7eeebib48","doi-asserted-by":"publisher","first-page":"6961","DOI":"10.1038\/s41467-021-27045-6","type":"journal-article","article-title":"Noise-induced barren plateaus in variational quantum algorithms","volume":"12","author":"Wang","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib49","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1137\/S0097539704445226","type":"journal-article","article-title":"The complexity of the local Hamiltonian problem","volume":"35","author":"Kempe","year":"2006","journal-title":"SIAM J. Comput."},{"key":"mlstae7eeebib50","doi-asserted-by":"publisher","first-page":"0900","DOI":"10.26421\/QIC8.10-2","type":"journal-article","article-title":"The complexity of quantum spin systems on a two-dimensional square lattice","volume":"8","author":"Oliveira","year":"2008","journal-title":"Quantum Inf. Comput."},{"key":"mlstae7eeebib51","doi-asserted-by":"crossref","DOI":"10.1109\/QCE65121.2025.00031","type":"preprint","article-title":"Qracle: a graph-neural-network-based parameter initializer for variational quantum eigensolvers","author":"Zhang","year":"2025"},{"key":"mlstae7eeebib52","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016","type":"preprint"},{"key":"mlstae7eeebib53","first-page":"pp 6519","type":"conference-proceedings","article-title":"Symmetric graph convolutional autoencoder for unsupervised graph representation learning","author":"Park","year":"2019"},{"key":"mlstae7eeebib54","doi-asserted-by":"crossref","DOI":"10.1088\/2632-2153\/adffe2","type":"preprint","article-title":"Guided graph compression for quantum graph neural networks","author":"Casals","year":"2025"},{"key":"mlstae7eeebib55","article-title":"Quantum graph neural networks","author":"Verdon","year":"2019","type":"preprint"},{"key":"mlstae7eeebib56","article-title":"Quantum graph attention network: a novel quantum multi-head attention mechanism for graph learning","author":"Ning","year":"2025","type":"preprint"},{"key":"mlstae7eeebib57","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v33i01.33013558","type":"preprint","article-title":"Hypergraph neural networks","author":"Feng","year":"2019"},{"key":"mlstae7eeebib58","first-page":"pp 6534","type":"conference-proceedings","article-title":"A survey on hypergraph neural networks: an in-depth and step-by-step guide","author":"Kim","year":"2024"},{"key":"mlstae7eeebib59","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1038\/s41467-019-10988-2","type":"journal-article","article-title":"An adaptive variational algorithm for exact molecular simulations on a quantum computer","volume":"10","author":"Grimsley","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstae7eeebib60","first-page":"pp 18182","type":"conference-proceedings","article-title":"Reinforcement learning for optimization of variational quantum circuit architectures","volume":"vol 34","author":"Ostaszewski","year":"2021"},{"key":"mlstae7eeebib61","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41534-022-00570-y","type":"journal-article","article-title":"Quantum circuit architecture search for variational quantum algorithms","volume":"8","author":"Du","year":"2022","journal-title":"npj Quantum Inf."},{"key":"mlstae7eeebib62","first-page":"pp 1525","type":"conference-proceedings","article-title":"Quantum machine learning architecture search via deep reinforcement learning","volume":"vol 1","author":"Dai","year":"2024"},{"key":"mlstae7eeebib63","type":"journal-article","article-title":"Graph-Neural-Quantum-Eigensolver: code for \u201cImproving Generalization and Trainability of Quantum Eigensolvers via Graph Neural Encoding\u201d","author":"Lee","year":"2026","journal-title":"GitHub"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T09:51:29Z","timestamp":1783331489000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae7eee"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":63,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,7,6]]},"published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae7eee","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"assertion":[{"value":"Improving generalization and trainability of quantum eigensolvers via graph neural encoding","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 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-02-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}