{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:10Z","timestamp":1777890130826,"version":"3.51.4"},"reference-count":47,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SW"],"published-print":{"date-parts":[[2024,11,22]]},"abstract":"<jats:p>Representation learning for link prediction is one of the leading approaches to deal with incompleteness problem of real world knowledge graphs. Such methods are often called knowledge graph embedding models which represent entities and relationships in knowledge graphs in continuous vector spaces. By doing this, semantic relationships and patterns can be captured in the form of compact vectors. In temporal knowledge graphs, the connection of temporal and relational information is crucial for representing facts accurately. Relations provide the semantic context for facts, while timestamps indicate the temporal validity of facts. The importance of time is different for the semantics of different facts. Some relations in some temporal facts are time-insensitive, while others are highly time-dependent. However, existing embedding models often overlook the time sensitivity of different facts in temporal knowledge graphs. These models tend to focus on effectively representing connection between individual components of quadruples, consequently capturing only a fraction of the overall knowledge. Ignoring importance of temporal properties reduces the ability of temporal knowledge graph embedding models in accurately capturing these characteristics. To address these challenges, we propose a novel embedding model based on temporal relevance, which can effectively capture the time sensitivity of semantics and better represent facts. This model operates within a complex space with real and imaginary parts to effectively embed temporal knowledge graphs. Specifically, the real part of the final embedding of our proposed model captures semantic characteristic with temporal sensitivity by learning the relational information and temporal information through transformation and attention mechanism. Simultaneously, the imaginary part of the embeddings learns the connections between different elements in the fact without predefined weights. Our approach is evaluated through extensive experiments on the link prediction task, where it majorly outperforms state-of-the-art models. The proposed model also demonstrates remarkable effectiveness in capturing the complexities of temporal knowledge graphs.<\/jats:p>","DOI":"10.3233\/sw-243699","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:43:31Z","timestamp":1732272211000},"page":"1-17","source":"Crossref","is-referenced-by-count":0,"title":["Temporal relevance for representing learning over temporal knowledge graphs"],"prefix":"10.1177","author":[{"given":"Bowen","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer, China University of Geosciences, Wuhan, China"},{"name":"Institute for Applied Informatics (InfAI), Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kossi","family":"Amouzouvi","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, TU Dresden, Dresden, Germany"},{"name":"Institute for Applied Informatics (InfAI), Dresden, Germany"},{"name":"Department of Mathematics, KNUST, Kumasi, Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjin","family":"Xu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maocai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, China University of Geosciences, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jens","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, TU Dresden, Dresden, Germany"},{"name":"Amazon, Germany"},{"name":"Institute for Applied Informatics (InfAI), Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sahar","family":"Vahdati","sequence":"additional","affiliation":[{"name":"Institute for Applied Informatics (InfAI), Dresden, Germany"},{"name":"Leibniz Information Centre for Science and Technology, TIB, Hannover, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/SW-243699_ref1","unstructured":"R.\u00a0Abboud, I.\u00a0Ceylan, T.\u00a0Lukasiewicz and T.\u00a0Salvatori, BoxE: A box embedding model for knowledge base completion, in: Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F.\u00a0Balcan and H.\u00a0Lin, eds, Vol.\u00a033, Curran Associates, Inc., 2020, pp.\u00a09649\u20139661, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/6dbbe6abe5f14af882ff977fc3f35501-Paper.pdf."},{"issue":"12","key":"10.3233\/SW-243699_ref2","doi-asserted-by":"publisher","first-page":"8825","DOI":"10.1109\/TPAMI.2021.3124805","article-title":"Bringing light into the dark: A large-scale evaluation of knowledge graph embedding models under a unified framework","volume":"44","author":"Ali","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/SW-243699_ref3","unstructured":"K.\u00a0Amouzouvi, B.\u00a0Song, S.\u00a0Vahdati and J.\u00a0Lehmann, Knowledge GeoGebra: Leveraging geometry of relation embeddings in knowledge graph completion, in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), N.\u00a0Calzolari, M.-Y.\u00a0Kan, V.\u00a0Hoste, A.\u00a0Lenci, S.\u00a0Sakti and N.\u00a0Xue, eds, ELRA and ICCL, Torino, Italia, 2024, pp.\u00a09832\u20139842, https:\/\/aclanthology.org\/2024.lrec-main.859."},{"key":"10.3233\/SW-243699_ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1522"},{"key":"10.3233\/SW-243699_ref5","unstructured":"I.\u00a0Balazevic, C.\u00a0Allen and T.\u00a0Hospedales, Multi-relational Poincar\u00e9 graph embeddings, in: Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d\u2019Alch\u00e9-Buc, E.\u00a0Fox and R.\u00a0Garnett, eds, Vol.\u00a032, Curran Associates, Inc., 2019, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/f8b932c70d0b2e6bf071729a4fa68dfc-Paper.pdf."},{"key":"10.3233\/SW-243699_ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53199-7_2"},{"key":"10.3233\/SW-243699_ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53199-7_6"},{"key":"10.3233\/SW-243699_ref8","unstructured":"A.\u00a0Bordes, N.\u00a0Usunier, A.\u00a0Garcia-Duran, J.\u00a0Weston and O.\u00a0Yakhnenko, Translating embeddings for modeling multi-relational data, in: Advances in Neural Information Processing Systems, C.J.\u00a0Burges, L.\u00a0Bottou, M.\u00a0Welling, Z.\u00a0Ghahramani and K.Q.\u00a0Weinberger, eds, Vol.\u00a026, Curran Associates, Inc., 2013, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf."},{"key":"10.3233\/SW-243699_ref9","doi-asserted-by":"publisher","DOI":"10.7910\/DVN\/28075"},{"key":"10.3233\/SW-243699_ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/734"},{"key":"10.3233\/SW-243699_ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3460210.3493566"},{"key":"10.3233\/SW-243699_ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7519"},{"key":"10.3233\/SW-243699_ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.617"},{"key":"10.3233\/SW-243699_ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.402"},{"key":"10.3233\/SW-243699_ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1225"},{"key":"10.3233\/SW-243699_ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"10.3233\/SW-243699_ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1516"},{"key":"10.3233\/SW-243699_ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5815"},{"key":"10.3233\/SW-243699_ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127680"},{"key":"10.3233\/SW-243699_ref20","unstructured":"T.\u00a0Lacroix, G.\u00a0Obozinski and N.\u00a0Usunier, Tensor decompositions for temporal knowledge base completion, in: International Conference on Learning Representations, 2020, https:\/\/openreview.net\/forum?id=rke2P1BFwS."},{"key":"10.3233\/SW-243699_ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191639"},{"key":"10.3233\/SW-243699_ref22","unstructured":"K.\u00a0Leetaru and P.A.\u00a0Schrodt, GDELT: Global data on events, location, and tone, 1979\u20132012, in: ISA Annual Convention, Vol.\u00a02, Citeseer, 2013, pp.\u00a01\u201349."},{"issue":"2","key":"10.3233\/SW-243699_ref23","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3233\/SW-140134","article-title":"Dbpedia\u00a0\u2013 a large-scale, multilingual knowledge base extracted from Wikipedia","volume":"6","author":"Lehmann","year":"2015","journal-title":"Semantic web"},{"key":"10.3233\/SW-243699_ref24","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.neucom.2023.01.079","article-title":"PTKE: Translation-based temporal knowledge graph embedding in polar coordinate system","volume":"529","author":"Liu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.3233\/SW-243699_ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119580"},{"issue":"7","key":"10.3233\/SW-243699_ref26","doi-asserted-by":"publisher","first-page":"7779","DOI":"10.1609\/aaai.v36i7.20746","article-title":"Temporal knowledge graph completion using box embeddings","volume":"36","author":"Messner","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/SW-243699_ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1466"},{"key":"10.3233\/SW-243699_ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2053"},{"key":"10.3233\/SW-243699_ref29","unstructured":"M.\u00a0Nickel, V.\u00a0Tresp and H.-P.\u00a0Kriegel, A three-way model for collective learning on multi-relational data, in: Proceedings of the 28th International Conference on International Conference on Machine Learning, ICML\u201911, Omnipress, Madison, WI, USA, 2011, pp.\u00a0809\u2013816. ISBN 9781450306195."},{"issue":"7","key":"10.3233\/SW-243699_ref30","doi-asserted-by":"publisher","first-page":"6471","DOI":"10.1609\/aaai.v35i7.16802","article-title":"ChronoR: Rotation based temporal knowledge graph embedding","volume":"35","author":"Sadeghian","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/SW-243699_ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126390"},{"key":"10.3233\/SW-243699_ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43418-1_36"},{"key":"10.3233\/SW-243699_ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"10.3233\/SW-243699_ref34","unstructured":"Z.\u00a0Sun, Z.-H.\u00a0Deng, J.-Y.\u00a0Nie and J.\u00a0Tang, RotatE: Knowledge graph embedding by relational rotation in complex space, in: International Conference on Learning Representations, 2019."},{"key":"10.3233\/SW-243699_ref35","unstructured":"T.\u00a0Trouillon, J.\u00a0Welbl, S.\u00a0Riedel, E.\u00a0Gaussier and G.\u00a0Bouchard, Complex embeddings for simple link prediction, in: Proceedings of the 33rd International Conference on Machine Learning, M.F.\u00a0Balcan and K.Q.\u00a0Weinberger, eds, Proceedings of Machine Learning Research, Vol.\u00a048, PMLR, New York, New York, USA, 2016, pp.\u00a02071\u20132080, https:\/\/proceedings.mlr.press\/v48\/trouillon16.html."},{"key":"10.3233\/SW-243699_ref36","unstructured":"A.\u00a0Vaswani, N.\u00a0Shazeer, N.\u00a0Parmar, J.\u00a0Uszkoreit, L.\u00a0Jones, A.N.\u00a0Gomez, L.\u00a0Kaiser and I.\u00a0Polosukhin, Attention is all you need, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, Curran Associates Inc., Red Hook, NY, USA, 2017, pp.\u00a06000\u20136010. ISBN 9781510860964."},{"issue":"10","key":"10.3233\/SW-243699_ref37","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","article-title":"Wikidata: A free collaborative knowledgebase","volume":"57","author":"Vrande\u010di\u0107","year":"2014","journal-title":"Communications of the ACM"},{"key":"10.3233\/SW-243699_ref38","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.ins.2022.12.019","article-title":"Temporal knowledge graph embedding via sparse transfer matrix","volume":"623","author":"Wang","year":"2023","journal-title":"Information Sciences"},{"key":"10.3233\/SW-243699_ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126249"},{"key":"10.3233\/SW-243699_ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8870"},{"key":"10.3233\/SW-243699_ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.202"},{"key":"10.3233\/SW-243699_ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.139"},{"key":"10.3233\/SW-243699_ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62419-4_37"},{"key":"10.3233\/SW-243699_ref44","unstructured":"B.\u00a0Yang, S.W.-T.\u00a0Yih, X.\u00a0He, J.\u00a0Gao and L.\u00a0Deng, Embedding entities and relations for learning and inference in knowledge bases, in: Proceedings of the International Conference on Learning Representations (ICLR) 2015, 2015, https:\/\/www.microsoft.com\/en-us\/research\/publication\/embedding-entities-and-relations-for-learning-and-inference-in-knowledge-bases\/."},{"key":"10.3233\/SW-243699_ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123295"},{"key":"10.3233\/SW-243699_ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557233"},{"key":"10.3233\/SW-243699_ref47","unstructured":"S.\u00a0Zhang, Y.\u00a0Tay, L.\u00a0Yao and Q.\u00a0Liu, Quaternion knowledge graph embeddings, in: Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d\u2019Alch\u00e9-Buc, E.\u00a0Fox and R.\u00a0Garnett, eds, Vol.\u00a032, Curran Associates, Inc., 2019, https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/d961e9f236177d65d21100592edb0769-Paper.pdf."}],"container-title":["Semantic Web"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/SW-243699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:27:38Z","timestamp":1777613258000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/SW-243699"}},"subtitle":[],"editor":[{"given":"Armin","family":"Haller","sequence":"additional","affiliation":[{"name":"Australian National University, Canberra, Australia"}],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":47,"URL":"https:\/\/doi.org\/10.3233\/sw-243699","relation":{},"ISSN":["2210-4968","1570-0844"],"issn-type":[{"value":"2210-4968","type":"electronic"},{"value":"1570-0844","type":"print"}],"subject":[],"published":{"date-parts":[[2024,11,22]]}}}