{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:03:01Z","timestamp":1787022181634,"version":"build-2736575974"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"crossref","award":["2022R1A2C3007921"],"award-info":[{"award-number":["2022R1A2C3007921"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["2022-0-00641"],"award-info":[{"award-number":["2022-0-00641"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2024-00509257"],"award-info":[{"award-number":["RS-2024-00509257"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2021-II212068"],"award-info":[{"award-number":["RS-2021-II212068"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>How can we accurately decompose a temporal irregular tensor along while incorporating a related knowledge graph tensor in both offline and online streaming settings? PARAFAC2 decomposition is widely applied to the analysis of irregular tensors consisting of matrices with varying row sizes. In both offline and online streaming scenarios, existing PARAFAC2 methods primarily focus on capturing dynamic features that evolve over time, since data irregularities often arise from temporal variations. However, these methods tend to overlook static features, such as knowledge-based information, which remain unchanged over time.<\/jats:p>\n                  <jats:p>\n                    In this paper, we propose KG-CTF (\n                    <jats:sc>\n                      <jats:underline>K<\/jats:underline>\n                    <\/jats:sc>\n                    nowledge Graph-based Coupled Tensor Factorization) and OKG-CTF (\n                    <jats:sc>\n                      <jats:underline>O<\/jats:underline>\n                    <\/jats:sc>\n                    nline Knowledge Graph-based Coupled Tensor Factorization), two coupled tensor factorization methods designed to effectively capture both dynamic and static features within an irregular tensor in offline and online streaming settings, respectively. To integrate knowledge graph tensors as static features, KG-CTF and OKG-CTF couple an irregular temporal tensor with a knowledge graph tensor by sharing a common axis. Additionally, both methods employ relational regularization to preserve the structural dependencies among the factor matrices of the knowledge graph tensor. To further enhance convergence speed, we utilize momentum-based update strategies for factor matrices. Through extensive experiments, we demonstrate that KG-CTF reduces error rates by up to 1.64\u00d7 compared to existing PARAFAC2 methods. Furthermore, OKG-CTF achieves up to 5.7\u00d7 faster running times compared to existing streaming approaches for each newly arriving tensor.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0336100","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:35:15Z","timestamp":1762972515000},"page":"e0336100","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Offline and online coupled tensor factorization with knowledge graph"],"prefix":"10.1371","volume":"20","author":[{"given":"SeungJoo","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Chan","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-6950","authenticated-orcid":true,"given":"U.","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"pone.0336100.ref001","doi-asserted-by":"crossref","first-page":"107841","DOI":"10.1016\/j.knosys.2021.107841","article-title":"Tucker decomposition-based temporal knowledge graph completion","volume":"238","author":"P Shao","year":"2022","journal-title":"Knowledge-Based Systems."},{"key":"pone.0336100.ref002","doi-asserted-by":"crossref","unstructured":"Bala\u017eevi\u0107 I, Allen C, Hospedales T. TuckER: tensor factorization for knowledge graph completion. In: EMNLP. 2019.","DOI":"10.18653\/v1\/D19-1522"},{"key":"pone.0336100.ref003","doi-asserted-by":"crossref","unstructured":"Zhang J, Lu CT, Cao B, Chang Y, Philip SY. Connecting emerging relationships from news via tensor factorization. In: Big Data. 2017.","DOI":"10.1109\/BigData.2017.8258048"},{"key":"pone.0336100.ref004","doi-asserted-by":"crossref","unstructured":"Padia A, Kalpakis K, Finin T. Inferring relations in knowledge graphs with tensor decompositions. In: Big Data. 2016.","DOI":"10.1109\/BigData.2016.7841096"},{"key":"pone.0336100.ref005","unstructured":"Nickel M, Tresp V, Kriegel HP. A three-way model for collective learning on multi-relational data. In: ICML. 2011."},{"issue":"5","key":"pone.0336100.ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3568682","article-title":"Static and streaming tucker decomposition for dense tensors","volume":"17","author":"J-G Jang","year":"2023","journal-title":"ACM Trans Knowl Discov Data."},{"key":"pone.0336100.ref007","doi-asserted-by":"crossref","unstructured":"Ahn D, Kim S, Kang U. Accurate online tensor factorization for temporal tensor streams with missing values. In: CIKM. 2021.","DOI":"10.1145\/3459637.3482048"},{"key":"pone.0336100.ref008","doi-asserted-by":"crossref","unstructured":"Jang JG, Kang U. Fast and memory-efficient tucker decomposition for answering diverse time range queries. In: KDD. 2021.","DOI":"10.1145\/3447548.3467290"},{"issue":"4","key":"pone.0336100.ref009","article-title":"DAO-CP: data-adaptive online CP decomposition for tensor stream","volume":"17","author":"S Son","year":"2022","journal-title":"PLoS One."},{"key":"pone.0336100.ref010","doi-asserted-by":"crossref","unstructured":"Oh S, Park N, Lee S, Kang U. Scalable tucker factorization for sparse tensors-algorithms and discoveries. In: ICDE. 2018.","DOI":"10.1109\/ICDE.2018.00104"},{"key":"pone.0336100.ref011","doi-asserted-by":"crossref","unstructured":"Jang JG, Kang U. D-tucker: Fast and memory-efficient tucker decomposition for dense tensors. In: ICDE. 2020.","DOI":"10.1109\/ICDE48307.2020.00186"},{"issue":"4","key":"pone.0336100.ref012","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1007\/s10994-021-06059-7","article-title":"Time-aware tensor decomposition for sparse tensors","volume":"111","author":"D Ahn","year":"2022","journal-title":"Mach Learn."},{"key":"pone.0336100.ref013","doi-asserted-by":"crossref","unstructured":"Jang JG, Park Y c, Kang U. Fast and accurate PARAFAC2 decomposition for time range queries on irregular tensors. In: CIKM. 2024.","DOI":"10.1145\/3627673.3679735"},{"key":"pone.0336100.ref014","doi-asserted-by":"crossref","unstructured":"Jang JG, Kang U. Dpar2: Fast and scalable parafac2 decomposition for irregular dense tensors. In: ICDE. 2022.","DOI":"10.1109\/ICDE53745.2022.00229"},{"key":"pone.0336100.ref015","doi-asserted-by":"crossref","unstructured":"Jang JG, Lee J, Park J, Kang U. Accurate PARAFAC2 decomposition for temporal irregular tensors with missing values. In: Big Data. 2022.","DOI":"10.1109\/BigData55660.2022.10020667"},{"key":"pone.0336100.ref016","doi-asserted-by":"crossref","unstructured":"Cheng Y, Haardt M. Efficient computation of the PARAFAC2 decomposition. In: ACSSC. 2019.","DOI":"10.1109\/IEEECONF44664.2019.9048813"},{"key":"pone.0336100.ref017","doi-asserted-by":"crossref","unstructured":"Perros I, Papalexakis EE, Wang F, Vuduc R, Searles E, Thompson M. SPARTan: Scalable PARAFAC2 for large & sparse data. In: KDD. 2017.","DOI":"10.1145\/3097983.3098014"},{"key":"pone.0336100.ref018","doi-asserted-by":"crossref","unstructured":"Kim J, Park KH, Jang JG, Kang U. Fast and accurate domain adaptation for irregular tensor decomposition. In: KDD. 2024.","DOI":"10.1145\/3637528.3671670"},{"key":"pone.0336100.ref019","doi-asserted-by":"crossref","unstructured":"Afshar A, Perros I, Park H, Defilippi C, Yan X, Stewart W. Taste: temporal and static tensor factorization for phenotyping electronic health records. In: CHIL. 2020.","DOI":"10.1145\/3368555.3384464"},{"key":"pone.0336100.ref020","doi-asserted-by":"crossref","unstructured":"Yin K, Afshar A, Ho JC, Cheung WK, Zhang C, Sun J. LogPar: logistic PARAFAC2 factorization for temporal binary data with missing values. In: KDD. 2020.","DOI":"10.1145\/3394486.3403213"},{"issue":"3044","key":"pone.0336100.ref021","first-page":"122215","article-title":"PARAFAC2: mathematical and technical notes","volume":"22","author":"RA Harshman","year":"1972","journal-title":"UCLA working papers in phonetics."},{"key":"pone.0336100.ref022","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1002\/(SICI)1099-128X(199905\/08)13:3\/4<275::AID-CEM543>3.0.CO;2-B","article-title":"PARAFAC2\u2014Part I. A direct fitting algorithm for the PARAFAC2 model","volume":"13","author":"HAL Kiers","year":"1999","journal-title":"J Chemometrics."},{"issue":"1","key":"pone.0336100.ref023","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF02296962","article-title":"Some uniqueness results for PARAFAC2","volume":"61","author":"JMF ten Berge","year":"1996","journal-title":"Psychometrika."},{"key":"pone.0336100.ref024","doi-asserted-by":"crossref","unstructured":"Roald M, Schenker C, Cohen JE, Acar E. PARAFAC2 AO-ADMM: constraints in all modes. In: EUSIPCO; 2021.","DOI":"10.23919\/EUSIPCO54536.2021.9615927"},{"key":"pone.0336100.ref025","article-title":"Simple embedding for link prediction in knowledge graphs","volume":"31","author":"SM Kazemi","year":"2018","journal-title":"Advances in Neural Information Processing Systems."},{"issue":"130","key":"pone.0336100.ref026","first-page":"1","article-title":"Knowledge graph completion via complex tensor factorization","volume":"18","author":"T Trouillon","year":"2017","journal-title":"Journal of Machine Learning Research."},{"key":"pone.0336100.ref027","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"A Bordes","year":"2013","journal-title":"Advances in neural information processing systems."},{"key":"pone.0336100.ref028","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/0024-3795(92)90031-5","article-title":"Krylov-subspace methods for the Sylvester equation","volume":"172","author":"DY Hu","year":"1992","journal-title":"Linear Algebra and its Applications."},{"key":"pone.0336100.ref029","doi-asserted-by":"crossref","DOI":"10.56021\/9781421407944","volume-title":"Matrix computations","author":"GH Golub","year":"2013"},{"key":"pone.0336100.ref030","doi-asserted-by":"crossref","unstructured":"Li XV. Findkg: dynamic knowledge graph with large language models for global finance. 2023. https:\/\/ssrn.com\/abstract=4608445","DOI":"10.2139\/ssrn.4608445"},{"key":"pone.0336100.ref031","doi-asserted-by":"crossref","unstructured":"Gujral E, Theocharous G, Papalexakis EE. Spade: Streaming parafac2 decomposition for large datasets. In: SDM. 2020.","DOI":"10.1137\/1.9781611976236.65"},{"key":"pone.0336100.ref032","doi-asserted-by":"crossref","unstructured":"Jang JG, Lee J, Park Y c, Kang U. Fast and accurate dual-way streaming PARAFAC2 for irregular tensors-algorithm and application. In: KDD. 2023.","DOI":"10.1145\/3580305.3599342"},{"key":"pone.0336100.ref033","doi-asserted-by":"crossref","unstructured":"Kwon T, Ko J, Jung J, Jang JG, Shin K. Compact decomposition of irregular tensors for data compression: from sparse to dense to high-order tensors. In: KDD. 2024.","DOI":"10.1145\/3637528.3671846"},{"key":"pone.0336100.ref034","doi-asserted-by":"crossref","unstructured":"Lee D, Shin K. Robust factorization of real-world tensor streams with patterns, missing values, and outliers. In: ICDE. IEEE; 2021.","DOI":"10.1109\/ICDE51399.2021.00078"},{"key":"pone.0336100.ref035","doi-asserted-by":"crossref","unstructured":"Zhou S, Erfani S, Bailey J. Online CP decomposition for sparse tensors. In: ICDM. IEEE; 2018.","DOI":"10.1109\/ICDM.2018.00202"},{"key":"pone.0336100.ref036","doi-asserted-by":"crossref","unstructured":"Park YC, Jang JG, Kang U. Fast and accurate partial fourier transform for time series data. In: KDD. 2021. p. 1309\u201318.","DOI":"10.1145\/3447548.3467293"},{"key":"pone.0336100.ref037","doi-asserted-by":"crossref","unstructured":"Park YC, Kim J, Kang U. Fast multidimensional partial fourier transform with automatic hyperparameter selection. In: KDD; 2024. p. 2328\u201339.","DOI":"10.1145\/3637528.3671667"},{"key":"pone.0336100.ref038","doi-asserted-by":"crossref","unstructured":"Park YC, Kim K, Kang U. PuzzleTensor: a method-agnostic data transformation for compact tensor factorization. In: KDD. 2025. p. 2234\u201344.","DOI":"10.1145\/3711896.3737095"},{"key":"pone.0336100.ref039","doi-asserted-by":"crossref","unstructured":"Lee S, Park YC, Kang U. Accurate coupled tensor factorization with knowledge graph. In: BigData. IEEE; 2024.","DOI":"10.1109\/BigData62323.2024.10825614"},{"key":"pone.0336100.ref040","doi-asserted-by":"crossref","unstructured":"Chen H, Li J. Collective tensor completion with multiple heterogeneous side information. In: Big Data. 2019.","DOI":"10.1109\/BigData47090.2019.9006072"},{"issue":"6","key":"pone.0336100.ref041","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0217316","article-title":"S3CMTF: fast, accurate, and scalable method for incomplete coupled matrix-tensor factorization","volume":"14","author":"D Choi","year":"2019","journal-title":"PLoS One."},{"key":"pone.0336100.ref042","article-title":"All-at-once optimization for coupled matrix and tensor factorizations","author":"E Acar","year":"2011","journal-title":"arXiv preprint"},{"key":"pone.0336100.ref043","doi-asserted-by":"crossref","unstructured":"Jeon I, Papalexakis EE, Kang U, Faloutsos C. Haten2: billion-scale tensor decompositions. In: ICDE. 2015.","DOI":"10.1109\/ICDE.2015.7113355"},{"key":"pone.0336100.ref044","doi-asserted-by":"crossref","unstructured":"Jeon B, Jeon I, Sael L, Kang U. Scout: scalable coupled matrix-tensor factorization-algorithm and discoveries. In: ICDE. 2016.","DOI":"10.1109\/ICDE.2016.7498292"},{"key":"pone.0336100.ref045","doi-asserted-by":"crossref","unstructured":"Gujral E, Theocharous G, Papalexakis EE. C3 APTION: constrainted coupled CP and PARAFAC2 tensor decomposition. In: ASONAM. 2020.","DOI":"10.1109\/ASONAM49781.2020.9381475"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T18:35:23Z","timestamp":1762972523000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336100"}},"subtitle":[],"editor":[{"given":"George","family":"Vousden","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":45,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0336100","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,12]]}}}