{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T04:27:01Z","timestamp":1766377621381,"version":"3.48.0"},"reference-count":51,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"name":"Fund for Scientific Research Flanders","award":["1SD8821N"],"award-info":[{"award-number":["1SD8821N"]}]},{"name":"Fund for Scientific Research Flanders","award":["1266521N"],"award-info":[{"award-number":["1266521N"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Soft. Eng. Knowl. Eng."],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Knowledge graph embeddings can be trained to infer which missing facts are likely to be true. For this, false training examples need to be derived from the available set of positive facts, so that the embedding models can learn to recognize the boundary between fact and fiction. Various negative sampling strategies have been proposed to tackle this issue, some of which have tried to make use of axiomatic knowledge claims to minimize the number of nonsensical negative samples being generated. By putting constraints on the construction of each candidate sample, these techniques have tried to maximize the number of true negatives outputted by the procedure. However, such strategies rely exclusively on binary interpretations of constraint-based reasoning and have so far also failed to incorporate literal-valued entities into the negative sampling procedure. To alleviate these shortcomings, we propose a negative sampling strategy based on a combination of fuzzy set theory and strict axiomatic semantics, which allow for the incorporation of literal-awareness when determining domain or range membership values. When evaluated on benchmark datasets AIFB and MUTAG, we found that these improvements offered significant performance gains across multiple metrics with respect to state of the art negative sampling techniques, suggesting that fuzzy semantics and literal-awareness can help to improve the quality of generated negative samples. On AIFB, our fuzzy negative sampling approach outperforms baselines on four metrics, with performance gains up to 17.14%. On MUTAG, our fuzzy negative sampling approach outperforms baselines on eight metrics, with performance gains up to 55.49%.<\/jats:p>","DOI":"10.1142\/s0218194025500421","type":"journal-article","created":{"date-parts":[[2025,8,9]],"date-time":"2025-08-09T03:09:58Z","timestamp":1754708998000},"page":"1-49","source":"Crossref","is-referenced-by-count":0,"title":["Fuzzy Constraints for Knowledge Graph Embeddings"],"prefix":"10.1142","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6157-5997","authenticated-orcid":false,"given":"Michael","family":"Weyns","sequence":"first","affiliation":[{"name":"IDLab, Ghent University-imec, Technologiepark-Zwijnaarde 126, B-9052 Gent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8931-8343","authenticated-orcid":false,"given":"Pieter","family":"Bonte","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KU Leuven Campus Kulak, Etienne Sabbelaan 53, 8500 Kortrijk, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4824-1199","authenticated-orcid":false,"given":"Filip","family":"De Turck","sequence":"additional","affiliation":[{"name":"IDLab, Ghent University-imec, Technologiepark-Zwijnaarde 126, B-9052 Gent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2529-5477","authenticated-orcid":false,"given":"Femke","family":"Ongenae","sequence":"additional","affiliation":[{"name":"IDLab, Ghent University-imec, Technologiepark-Zwijnaarde 126, B-9052 Gent, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"issue":"1","key":"S0218194025500421BIB001","first-page":"13","volume":"11","author":"Cudr\u00e9-Mauroux P.","year":"2020","journal-title":"Semantic Web"},{"key":"S0218194025500421BIB002","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1105"},{"key":"S0218194025500421BIB003","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1951-8_73"},{"key":"S0218194025500421BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"S0218194025500421BIB005","unstructured":"B. Kotnis and V. Nastase, Analysis of the impact of negative sampling on link prediction in knowledge graphs, arXiv:1708.06816."},{"key":"S0218194025500421BIB006","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1165"},{"key":"S0218194025500421BIB007","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25007-6_37"},{"key":"S0218194025500421BIB008","unstructured":"A. Bernardi and L. Costabello, Domain and range aware synthetic negatives generation for knowledge graph embedding models, arXiv:2411.14858."},{"key":"S0218194025500421BIB009","first-page":"323","volume-title":"Proc. Int. Workshop Artificial Intelligence and Pattern Recognition","author":"L\u00f3pez-Rodr\u00edguez Y. A.","year":"2023"},{"key":"S0218194025500421BIB010","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_24"},{"issue":"4","key":"S0218194025500421BIB011","first-page":"617","volume":"12","author":"Gesese G. A.","year":"2021","journal-title":"Semantic Web"},{"key":"S0218194025500421BIB012","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46547-0_20"},{"key":"S0218194025500421BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2483592"},{"key":"S0218194025500421BIB014","first-page":"2787","volume-title":"Advances in Neural Information Processing Systems","author":"Bordes A.","year":"2013"},{"key":"S0218194025500421BIB015","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8870"},{"key":"S0218194025500421BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852374"},{"key":"S0218194025500421BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545743"},{"key":"S0218194025500421BIB018","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0118-0_42"},{"key":"S0218194025500421BIB019","unstructured":"S. Dash and A. Gliozzo, Distributional negative sampling for knowledge base completion, arXiv:1908.06178."},{"key":"S0218194025500421BIB020","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119122"},{"key":"S0218194025500421BIB021","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106358"},{"key":"S0218194025500421BIB022","unstructured":"K. Ahrabian, A. Feizi, Y. Salehi, W. L. Hamilton and A. J. Bose, Structure aware negative sampling in knowledge graphs, arXiv:2009.11355."},{"key":"S0218194025500421BIB023","unstructured":"M. R. A. H. Rony, M. M. Alam, S. Ali, J. Lehmann and S. Vahdati, Lemon: Language model for negative sampling of knowledge graph embeddings, arXiv:2203.04703."},{"key":"S0218194025500421BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93413-2_46"},{"key":"S0218194025500421BIB025","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4007"},{"key":"S0218194025500421BIB026","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-60626-7_2"},{"key":"S0218194025500421BIB027","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77385-4_26"},{"key":"S0218194025500421BIB028","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1009"},{"key":"S0218194025500421BIB029","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16879"},{"key":"S0218194025500421BIB030","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01016-3"},{"key":"S0218194025500421BIB031","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_40"},{"key":"S0218194025500421BIB032","unstructured":"B. Yang, W.t. Yih, X. He, J. Gao and L. Deng, Embedding entities and relations for learning and inference in knowledge bases, arXiv:1412.6575."},{"key":"S0218194025500421BIB033","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(65)90241-X"},{"key":"S0218194025500421BIB034","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0114(97)00080-8"},{"key":"S0218194025500421BIB035","unstructured":"D. McGuinness and C. Welty, OWL web ontology language guide, W3C recommendation, W3C (2004), http:\/\/www.w3.org\/TR\/2004\/REC-owl-guide-20040210\/."},{"key":"S0218194025500421BIB036","unstructured":"P. Hayes and P. Patel-Schneider, RDF 1.1 semantics, W3C recommendation, W3C (2014), https:\/\/www.w3.org\/TR\/2014\/REC-rdf11-mt-20140225\/."},{"volume-title":"Proc. Workshop Deep Learning for Knowledge Graphs","year":"2020","author":"Weyns M.","key":"S0218194025500421BIB037"},{"key":"S0218194025500421BIB038","unstructured":"R. Guha and D. Brickley, RDF schema 1.1, W3C recommendation, W3C (2014), http:\/\/www.w3.org\/TR\/2014\/REC-rdf-schema-20140225\/."},{"key":"S0218194025500421BIB039","unstructured":"H. Knublauch and D. Kontokostas, Shapes constraint language (SHACL), W3C recommendation, W3C (2017), https:\/\/www.w3.org\/TR\/2017\/REC-shacl-20170720\/."},{"key":"S0218194025500421BIB040","unstructured":"G. Schreiber and M. Dean, OWL web ontology language reference, W3C recommendation, W3C (2004), http:\/\/www.w3.org\/TR\/2004\/REC-owl-ref-20040210\/."},{"key":"S0218194025500421BIB041","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380226"},{"key":"S0218194025500421BIB042","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30793-6_20"},{"issue":"9","key":"S0218194025500421BIB043","first-page":"1345","volume":"6","author":"Banerjee A.","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"S0218194025500421BIB044","unstructured":"P. Pezeshkpour, L. Chen and S. Singh, Embedding multimodal relational data for knowledge base completion, arXiv:1809.01341."},{"key":"S0218194025500421BIB045","first-page":"1188","volume-title":"Proc. Int. Conf. Machine Learning","author":"Le Q.","year":"2014"},{"key":"S0218194025500421BIB046","unstructured":"K. Cho, B. Van Merri\u00ebnboer C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk and Y. Bengio, Learning phrase representations using rnn encoder-decoder for statistical machine translation, arXiv:1406.1078."},{"key":"S0218194025500421BIB047","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46523-4_30"},{"key":"S0218194025500421BIB048","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380599"},{"volume-title":"EDBT\/ICDT Workshops","year":"2020","author":"Rossi A.","key":"S0218194025500421BIB049"},{"key":"S0218194025500421BIB050","first-page":"1059","volume-title":"Proc. Conf. Uncertainty in Artificial Intelligence","author":"Mohamed A.","year":"2020"},{"key":"S0218194025500421BIB051","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7917"}],"container-title":["International Journal of Software Engineering and Knowledge Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218194025500421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T04:23:56Z","timestamp":1766377436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218194025500421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":51,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1142\/S0218194025500421"],"URL":"https:\/\/doi.org\/10.1142\/s0218194025500421","relation":{},"ISSN":["0218-1940","1793-6403"],"issn-type":[{"type":"print","value":"0218-1940"},{"type":"electronic","value":"1793-6403"}],"subject":[],"published":{"date-parts":[[2025,10,25]]}}}