{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T03:40:28Z","timestamp":1771299628718,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:00:00Z","timestamp":1663718400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:00:00Z","timestamp":1663718400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["RTI2018-101045- A-C22"],"award-info":[{"award-number":["RTI2018-101045- A-C22"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["05470RB-C31"],"award-info":[{"award-number":["05470RB-C31"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019927","name":"Universidad de Deusto","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100019927","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Knowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add <jats:inline-formula><jats:alternatives><jats:tex-math>$$l_1$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mi>l<\/mml:mi>\n                    <mml:mn>1<\/mml:mn>\n                  <\/mml:msub>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.<\/jats:p>","DOI":"10.1007\/s00521-022-07796-z","type":"journal-article","created":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T14:02:57Z","timestamp":1663768977000},"page":"787-797","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Regularized online tensor factorization for sparse knowledge graph embeddings"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7366-9579","authenticated-orcid":false,"given":"Unai","family":"Zulaika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aitor","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"L\u00f3pez-de-Ipi\u00f1a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,21]]},"reference":[{"key":"7796_CR1","unstructured":"Allen C, Balazevic I, Hospedales T (2021) Interpreting knowledge graph relation representation from word embeddings. In: International conference on learning representations, https:\/\/openreview.net\/forum?id=gLWj29369lW"},{"key":"7796_CR2","doi-asserted-by":"crossref","unstructured":"Balazevic I, Allen C, Hospedales T (2019) TuckER: tensor factorization for knowledge graph completion. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, pp. 5185\u20135194, https:\/\/doi.org\/10.18653\/v1\/D19-1522 https:\/\/aclanthology.org\/D19-1522","DOI":"10.18653\/v1\/D19-1522"},{"key":"7796_CR3","doi-asserted-by":"crossref","unstructured":"Barbieri N, Bonchi F, Manco G (2014) Who to follow and why: link prediction with explanations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1266\u20131275","DOI":"10.1145\/2623330.2623733"},{"key":"7796_CR4","unstructured":"Bordes A, Usunier N, Garcia-Duran A, et\u00a0al (2013) Translating embeddings for modeling multi-relational data. In: Burges C, Bottou L, Welling M, et\u00a0al (eds) Advances in neural information processing systems, vol\u00a026. Curran Associates, Inc., https:\/\/proceedings.neurips.cc\/paper\/2013\/file\/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf"},{"key":"7796_CR5","unstructured":"Chandrahas , Sengupta T, Pragadeesh C, et\u00a0al (2020) Inducing interpretability in knowledge graph embeddings. In: Proceedings of the 17th international conference on natural language processing (ICON). NLP Association of India (NLPAI), Indian Institute of Technology Patna, Patna, India, pp. 70\u201375, https:\/\/aclanthology.org\/2020.icon-main.9"},{"key":"7796_CR6","unstructured":"Chao SK, Wang Z, Xing Y, et\u00a0al (2020) Directional pruning of deep neural networks. In: Larochelle H, Ranzato M, Hadsell R, et\u00a0al (eds) Advances in neural information processing systems, vol\u00a033. Curran Associates, Inc., pp. 13986\u201313998, https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/a09e75c5c86a7bf6582d2b4d75aad615-Paper.pdf"},{"key":"7796_CR7","doi-asserted-by":"crossref","unstructured":"Dettmers T, Minervini P, Stenetorp P, et\u00a0al (2018) Convolutional 2d knowledge graph embeddings. In: Proceedings of the thirty-second AAAI conference on artificial intelligence and thirtieth innovative applications of artificial intelligence conference and eighth AAAI symposium on educational advances in artificial intelligence. AAAI Press, AAAI\u201918\/IAAI\u201918\/EAAI\u201918","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"7796_CR8","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121\u20132159","journal-title":"J Mach Learn Res"},{"key":"7796_CR9","doi-asserted-by":"crossref","unstructured":"Engelen van JE, Boekhout HD, Takes FW (2016) Explainable and efficient link prediction in real-world network data. In: International symposium on intelligent data analysis, Springer, pp. 295\u2013307","DOI":"10.1007\/978-3-319-46349-0_26"},{"key":"7796_CR10","doi-asserted-by":"publisher","unstructured":"Faruqui M, Tsvetkov Y, Yogatama D, et\u00a0al (2015) Sparse overcomplete word vector representations. In: Proceedings of the 53rd annual meeting of the association for computational Linguistics and the 7th international joint conference on natural language processing (Volume 1: Long Papers). Association for computational Linguistics, Beijing, China, pp. 1491\u20131500, https:\/\/doi.org\/10.3115\/v1\/P15-1144, https:\/\/www.aclweb.org\/anthology\/P15-1144","DOI":"10.3115\/v1\/P15-1144"},{"key":"7796_CR11","doi-asserted-by":"crossref","unstructured":"Fatemi B, Ravanbakhsh S, Poole D (2019) Improved knowledge graph embedding using background taxonomic information. In: Proceedings of the AAAI conference on artificial intelligence, pp. 3526\u20133533","DOI":"10.1609\/aaai.v33i01.33013526"},{"key":"7796_CR12","unstructured":"Gusmao AC, Correia AHC, De\u00a0Bona G, et\u00a0al (2018) Interpreting embedding models of knowledge bases: a pedagogical approach. arXiv preprint arXiv:1806.09504"},{"issue":"2","key":"7796_CR13","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1287\/mksc.1.2.205","volume":"1","author":"RA Harshman","year":"1982","unstructured":"Harshman RA, Green PE, Wind Y et al (1982) A model for the analysis of asymmetric data in marketing research. Mark Sci 1(2):205\u2013242","journal-title":"Mark Sci"},{"key":"7796_CR14","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on international conference on machine learning - Volume 37. JMLR.org, ICML\u201915, pp. 448\u2013456"},{"key":"7796_CR15","doi-asserted-by":"publisher","unstructured":"Kadlec R, Bajgar O, Kleindienst J (2017) Knowledge base completion: baselines strike back. In: Proceedings of the 2nd workshop on representation learning for NLP. Association for computational Linguistics, Vancouver, Canada, pp. 69\u201374, https:\/\/doi.org\/10.18653\/v1\/W17-2609, https:\/\/aclanthology.org\/W17-2609","DOI":"10.18653\/v1\/W17-2609"},{"key":"7796_CR16","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"7796_CR17","unstructured":"Lacroix T, Usunier N, Obozinski G (2018) Canonical tensor decomposition for knowledge base completion. In: International conference on machine learning, PMLR, pp. 2863\u20132872"},{"key":"7796_CR18","unstructured":"Lacroix T, Obozinski G, Usunier N (2020) Tensor decompositions for temporal knowledge base completion. In: International conference on learning representations, https:\/\/openreview.net\/forum?id=rke2P1BFwS"},{"issue":"6755","key":"7796_CR19","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788\u2013791","journal-title":"Nature"},{"issue":"7","key":"7796_CR20","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.3390\/electronics11071058","volume":"11","author":"Z Liang","year":"2022","unstructured":"Liang Z, Yang J, Liu H et al (2022) Seatte: An embedding model based on separating attribute space for knowledge graph completion. Electronics 11(7):1058","journal-title":"Electronics"},{"key":"7796_CR21","doi-asserted-by":"publisher","first-page":"e357","DOI":"10.7717\/peerj-cs.357","volume":"7","author":"I Makarov","year":"2021","unstructured":"Makarov I, Kiselev D, Nikitinsky N et al (2021) Survey on graph embeddings and their applications to machine learning problems on graphs. PeerJ Comput Sci 7:e357","journal-title":"PeerJ Comput Sci"},{"key":"7796_CR22","doi-asserted-by":"crossref","unstructured":"Minervini P, Costabello L, Mu\u00f1oz E, et\u00a0al (2017) Regularizing knowledge graph embeddings via equivalence and inversion axioms. In: Joint European conference on machine learning and knowledge discovery in databases, Springer, pp. 668\u2013683","DOI":"10.1007\/978-3-319-71249-9_40"},{"key":"7796_CR23","first-page":"1933","volume":"2012","author":"B Murphy","year":"2012","unstructured":"Murphy B, Talukdar P, Mitchell T (2012) Learning effective and interpretable semantic models using non-negative sparse embedding. Proc COLING 2012:1933\u20131950","journal-title":"Proc COLING"},{"key":"7796_CR24","volume-title":"The big book of concepts","author":"G Murphy","year":"2004","unstructured":"Murphy G (2004) The big book of concepts. MIT Press, Cambridge"},{"key":"7796_CR25","unstructured":"Nickel M, Tresp V, Kriegel HP (2011) A three-way model for collective learning on multi-relational data. In: Icml, pp. 809\u2013816"},{"key":"7796_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2019.01.004","author":"A Padia","year":"2019","unstructured":"Padia A, Kalpakis K, Ferraro F et al (2019) Knowledge graph fact prediction via knowledge-enriched tensor factorization. Web Semant. https:\/\/doi.org\/10.1016\/j.websem.2019.01.004","journal-title":"Web Semant"},{"key":"7796_CR27","doi-asserted-by":"publisher","unstructured":"Panigrahi A, Simhadri HV, Bhattacharyya C (2019) Word2Sense: Sparse interpretable word embeddings. In: Proceedings of the 57th annual meeting of the association for computational Linguistics. Association for computational Linguistics, Florence, Italy, pp 5692\u20135705, https:\/\/doi.org\/10.18653\/v1\/P19-1570, https:\/\/www.aclweb.org\/anthology\/P19-1570","DOI":"10.18653\/v1\/P19-1570"},{"issue":"3","key":"7796_CR28","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1561\/2400000003","volume":"1","author":"N Parikh","year":"2014","unstructured":"Parikh N, Boyd S et al (2014) Proximal algorithms. Found Trends\u00ae Optim 1(3):127\u2013239","journal-title":"Found Trends\u00ae Optim"},{"issue":"2","key":"7796_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3424672","volume":"15","author":"A Rossi","year":"2021","unstructured":"Rossi A, Barbosa D, Firmani D et al (2021) Knowledge graph embedding for link prediction: a comparative analysis. ACM Trans Knowl Discov Data (TKDD) 15(2):1\u201349","journal-title":"ACM Trans Knowl Discov Data (TKDD)"},{"key":"7796_CR30","unstructured":"Ruffinelli D, Broscheit S, Gemulla R (2020) You can teach an old dog new tricks! on training knowledge graph embeddings. In: International conference on learning representations, https:\/\/openreview.net\/forum?id=BkxSmlBFvr"},{"key":"7796_CR31","unstructured":"Schunn CD (1999) The presence and absence of category knowledge in lsa. In: 21st annual conference of the cognitive science society, Citeseer"},{"issue":"2","key":"7796_CR32","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1561\/2200000018","volume":"4","author":"S Shalev-Shwartz","year":"2012","unstructured":"Shalev-Shwartz S et al (2012) Online learning and online convex optimization. Found Trends\u00ae Mach Learn 4(2):107\u2013194","journal-title":"Found Trends\u00ae Mach Learn"},{"issue":"1","key":"7796_CR33","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"7796_CR34","doi-asserted-by":"publisher","unstructured":"Subramanian A, Pruthi D, Jhamtani H, et\u00a0al (2018) Spine: Sparse interpretable neural embeddings. In: Proceedings of the AAAI conference on artificial intelligence, vol. 32(1). https:\/\/doi.org\/10.1609\/aaai.v32i1.11935, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11935","DOI":"10.1609\/aaai.v32i1.11935"},{"key":"7796_CR35","unstructured":"Sun F, Guo J, Lan Y, et\u00a0al (2016) Sparse word embeddings using l1 regularized online learning. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, AAAI Press, pp. 2915\u20132921"},{"key":"7796_CR36","doi-asserted-by":"publisher","unstructured":"Toutanova K, Chen D, Pantel P, et\u00a0al (2015) Representing text for joint embedding of text and knowledge bases. In: Proceedings of the 2015 conference on empirical methods in natural language processing. Association for computational Linguistics, Lisbon, Portugal, pp. 1499\u20131509, https:\/\/doi.org\/10.18653\/v1\/D15-1174, https:\/\/www.aclweb.org\/anthology\/D15-1174","DOI":"10.18653\/v1\/D15-1174"},{"issue":"1","key":"7796_CR37","first-page":"4735","volume":"18","author":"T Trouillon","year":"2017","unstructured":"Trouillon T, Dance CR, Gaussier \u00c9 et al (2017) Knowledge graph completion via complex tensor factorization. J Mach Learn Res 18(1):4735\u20134772","journal-title":"J Mach Learn Res"},{"key":"7796_CR38","first-page":"110","volume-title":"Contributions to mathematical psychology","author":"LR Tucker","year":"1964","unstructured":"Tucker LR (1964) The extension of factor analysis to three-dimensional matrices. In: Gulliksen H, Frederiksen N (eds) Contributions to mathematical psychology. Holt Rinehart and Winston, New York, pp 110\u2013127"},{"key":"7796_CR39","doi-asserted-by":"crossref","unstructured":"Wan G, Du B (2021) Gaussianpath:a bayesian multi-hop reasoning framework for knowledge graph reasoning. In: Proceedings of the AAAI conference on artificial intelligence 35(5):4393\u20134401. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16565","DOI":"10.1609\/aaai.v35i5.16565"},{"issue":"1","key":"7796_CR40","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s11280-019-00711-y","volume":"23","author":"G Wan","year":"2020","unstructured":"Wan G, Du B, Pan S et al (2020) Adaptive knowledge subgraph ensemble for robust and trustworthy knowledge graph completion. World Wide Web 23(1):471\u2013490","journal-title":"World Wide Web"},{"key":"7796_CR41","doi-asserted-by":"publisher","unstructured":"Wang Y, Ruffinelli D, Gemulla R, et\u00a0al (2019) On evaluating embedding models for knowledge base completion. In: Proceedings of the 4th workshop on representation learning for NLP (RepL4NLP-2019). Association for computational Linguistics, Florence, Italy, pp. 104\u2013112, https:\/\/doi.org\/10.18653\/v1\/W19-4313, https:\/\/aclanthology.org\/W19-4313","DOI":"10.18653\/v1\/W19-4313"},{"issue":"Oct","key":"7796_CR42","first-page":"2543","volume":"11","author":"L Xiao","year":"2010","unstructured":"Xiao L (2010) Dual averaging methods for regularized stochastic learning and online optimization. J Mach Learn Res 11(Oct):2543\u20132596","journal-title":"J Mach Learn Res"},{"key":"7796_CR43","doi-asserted-by":"publisher","unstructured":"Xie Q, Ma X, Dai Z, et\u00a0al (2017) An interpretable knowledge transfer model for knowledge base completion. In: Proceedings of the 55th annual meeting of the association for computational Linguistics (Volume 1: long papers). Association for computational Linguistics, Vancouver, Canada, pp. 950\u2013962, https:\/\/doi.org\/10.18653\/v1\/P17-1088, https:\/\/aclanthology.org\/P17-1088","DOI":"10.18653\/v1\/P17-1088"},{"key":"7796_CR44","unstructured":"Yang B, Yih W, He X, et\u00a0al (2015) Embedding entities and relations for learning and inference in knowledge bases. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, San Diego, CA, US. http:\/\/arxiv.org\/abs\/1412.6575"},{"key":"7796_CR45","unstructured":"Zhang Z, Cai J, Wang J (2020) Duality-induced regularizer for tensor factorization based knowledge graph completion. In: Proceedings of the 34th international conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA"},{"key":"7796_CR46","unstructured":"Zhong Q, Ding L, Liu J, et\u00a0al (2022) Knowledge graph augmented network towards multiview representation learning for aspect-based sentiment analysis. arXiv preprint arXiv:2201.04831"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07796-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07796-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07796-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T06:15:54Z","timestamp":1673072154000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07796-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,21]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["7796"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07796-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,21]]},"assertion":[{"value":"17 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}