{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T20:07:06Z","timestamp":1766088426708,"version":"3.40.3"},"reference-count":31,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Joint project of Kyoto University and Toyota Motor : Advanced Mathematical Science for Mobility Society"},{"name":"The Center of Innovations for Sustainable Quantum AI","award":["JPMJPF2221"],"award-info":[{"award-number":["JPMJPF2221"]}]},{"name":"the Endowed Project for Quantum Software Research and Education, The University of Tokyo"},{"name":"JSPS KAKENHI","award":["20K03766"],"award-info":[{"award-number":["20K03766"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Based on the tensor tree network with the Born machine framework, we propose a general method for constructing a generative model by expressing the target distribution function as the amplitude of the quantum wave function represented by a tensor tree. The key idea is dynamically optimizing the tree structure that minimizes the bond mutual information. The proposed method offers enhanced performance and uncovers hidden relational structures in the target data. We illustrate potential practical applications with four examples: (i) random patterns, (ii) QMNIST handwritten digits, (iii) Bayesian networks, and (iv) the pattern of stock price fluctuation pattern in S&amp;P500. In (i) and (ii), the strongly correlated variables were concentrated near the center of the network; in (iii), the causality pattern was identified; and in (iv), a structure corresponding to the eleven sectors emerged.<\/jats:p>","DOI":"10.1088\/2632-2153\/adc2c7","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T22:57:17Z","timestamp":1742425037000},"page":"025002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Tensor tree learns hidden relational structures in data to construct generative models"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0231-7880","authenticated-orcid":true,"given":"Kenji","family":"Harada","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4334-7293","authenticated-orcid":true,"given":"Tsuyoshi","family":"Okubo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8440-6037","authenticated-orcid":false,"given":"Naoki","family":"Kawashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"mlstadc2c7bib1","article-title":"Learning both weights and connections for efficient neural network","volume":"vol 28","author":"Han","year":"2015"},{"key":"mlstadc2c7bib2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031012","article-title":"Unsupervised generative modeling using matrix product states","volume":"8","author":"Han","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstadc2c7bib3","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41534-019-0157-8","article-title":"A generative modeling approach for benchmarking and training shallow quantum circuits","volume":"5","author":"Benedetti","year":"2019","journal-title":"npj Quantum Inf."},{"key":"mlstadc2c7bib4","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41534-020-00288-9","article-title":"The Born supremacy: quantum advantage and training of an Ising Born machine","volume":"6","author":"Coyle","year":"2020","journal-title":"npj Quantum Inf."},{"key":"mlstadc2c7bib5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s42005-024-01552-6","article-title":"A framework for demonstrating practical quantum advantage: comparing quantum against classical generative models","volume":"7","author":"Hibat-Allah","year":"2024","journal-title":"Commun. Phys."},{"key":"mlstadc2c7bib6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.062324","article-title":"Differentiable learning of quantum circuit Born machines","volume":"98","author":"Liu","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstadc2c7bib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.16.044057","article-title":"Variational inference with a quantum computer","volume":"16","author":"Benedetti","year":"2021","journal-title":"Phys. Rev. Appl."},{"key":"mlstadc2c7bib8","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.aop.2014.06.013","article-title":"A practical introduction to tensor networks: matrix product states and projected entangled pair states","volume":"349","author":"Or\u00fas","year":"2014","journal-title":"Ann. Phys., NY"},{"year":"2023","author":"Xiang","key":"mlstadc2c7bib9"},{"key":"mlstadc2c7bib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.99.155131","article-title":"Tree tensor networks for generative modeling","volume":"99","author":"Cheng","year":"2019","journal-title":"Phys. Rev. B"},{"key":"mlstadc2c7bib11","article-title":"Supervised learning with tensor networks","volume":"vol 29","author":"Stoudenmire","year":"2016"},{"key":"mlstadc2c7bib12","article-title":"Tensorizing neural networks","volume":"vol 28","author":"Novikov","year":"2015"},{"key":"mlstadc2c7bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.132.197301","article-title":"Combining reinforcement learning and tensor networks, with an application to dynamical large deviations","volume":"132","author":"Gillman","year":"2024","journal-title":"Phys. Rev. Lett."},{"key":"mlstadc2c7bib14","doi-asserted-by":"publisher","first-page":"8367","DOI":"10.1038\/s41467-023-43908-6","article-title":"synergistic pretraining of parametrized quantum circuits via tensor networks","volume":"14","author":"Rudolph","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstadc2c7bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.80.032319","article-title":"Correlations in local measurements on a quantum state and complementarity as an explanation of nonclassicality","volume":"80","author":"Wu","year":"2009","journal-title":"Phys. Rev. A"},{"key":"mlstadc2c7bib16","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac44a9","article-title":"Mutual information scaling for tensor network machine learning","volume":"3","author":"Convy","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstadc2c7bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.013031","article-title":"Automatic structural optimization of tree tensor networks","volume":"5","author":"Hikihara","year":"2023","journal-title":"Phys. Rev. Res."},{"year":"2024","author":"Hikihara","article-title":"Visualization of entanglement geometry by structural optimization of tree tensor network","key":"mlstadc2c7bib18"},{"year":"2025","author":"Hikihara","article-title":"Improving accuracy of tree-tensor network approach by optimization of network structure","key":"mlstadc2c7bib19"},{"key":"mlstadc2c7bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.74.022320","article-title":"Classical simulation of quantum many-body systems with a tree tensor network","volume":"74","author":"Shi","year":"2006","journal-title":"Phys. Rev. A"},{"key":"mlstadc2c7bib21","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1137\/070709967","article-title":"On the complexity of nonnegative matrix factorization","volume":"20","author":"Vavasis","year":"2010","journal-title":"SIAM J. Optim."},{"key":"mlstadc2c7bib22","article-title":"Cold case: the lost mnist digits","volume":"vol 32","author":"Yadav","year":"2019"},{"key":"mlstadc2c7bib23","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"year":"1988","author":"Pearl","key":"mlstadc2c7bib24"},{"key":"mlstadc2c7bib25","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/s13748-019-00194-y","article-title":"A survey on Bayesian network structure learning from data","volume":"8","author":"Scanagatta","year":"2019","journal-title":"Prog. Artif. Intell."},{"key":"mlstadc2c7bib26","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TIT.1968.1054142","article-title":"Approximating discrete probability distributions with dependence trees","volume":"14","author":"Chow","year":"1968","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstadc2c7bib27","doi-asserted-by":"publisher","first-page":"222","DOI":"10.48550\/arXiv.1304.2736","article-title":"The recovery of causal poly-trees from statistical data","volume":"3","author":"Rebane","year":"1989","journal-title":"Artif. Intell."},{"year":"2021","author":"Miller","article-title":"Probabilistic graphical models and tensor networks: a hybrid","key":"mlstadc2c7bib28"},{"key":"mlstadc2c7bib29","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s42484-022-00095-9","article-title":"Decohering tensor network quantum machine learning models","volume":"5","author":"Liao","year":"2023","journal-title":"Quantum Mach. Intell."},{"key":"mlstadc2c7bib30","article-title":"adaptive tensor tree modeling","author":"Harada","year":"2024","unstructured":"Harada K 2024 adaptive tensor tree modeling (available at: https:\/\/github.com\/KenjiHarada\/adaptive-tensor-tree-generative-modeling )"},{"key":"mlstadc2c7bib31","first-page":"pp 79","article-title":"Application of tensor network formalism for processing tensor data","author":"Harada","year":"2024"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T14:02:50Z","timestamp":1743516170000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adc2c7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,4,1]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adc2c7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,4,1]]},"assertion":[{"value":"Tensor tree learns hidden relational structures in data to construct generative models","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-10-29","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-03-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-01","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}