{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T11:40:05Z","timestamp":1756208405782,"version":"3.44.0"},"reference-count":41,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000},"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":[[2024,5,14]]},"abstract":"<jats:p>Knowledge graph reasoning (KGR) aims to infer new knowledge or detect noises, which is essential for improving the quality of knowledge graphs. Recently, various KGR techniques, such as symbolic- and embedding-based methods, have been proposed and shown strong reasoning ability. Symbolic-based reasoning methods infer missing triples according to predefined rules or ontologies. Although rules and axioms have proven effective, it is difficult to obtain them. Embedding-based reasoning methods represent entities and relations as vectors, and complete KGs via vector computation. However, they mainly rely on structural information and ignore implicit axiom information not predefined in KGs but can be reflected in data. That is, each correct triple is also a logically consistent triple and satisfies all axioms. In this paper, we propose a novel NeuRal Axiom Network (NeuRAN) framework that combines explicit structural and implicit axiom information without introducing additional ontologies. Specifically, the framework consists of a KG embedding module that preserves the semantics of triples and five axiom modules that encode five kinds of implicit axioms. These axioms correspond to five typical object property expression axioms defined in OWL2, including ObjectPropertyDomain, ObjectPropertyRange, DisjointObjectProperties, IrreflexiveObjectProperty and AsymmetricObjectProperty. The KG embedding module and axiom modules compute the scores that the triple conforms to the semantics and the corresponding axioms, respectively. Compared with KG embedding models and CKRL, our method achieves comparable performance on noise detection and triple classification and achieves significant performance on link prediction. Compared with TransE and TransH, our method improves the link prediction performance on the Hits@1 metric by 22.0% and 20.8% on WN18RR-10% dataset, respectively.<\/jats:p>","DOI":"10.3233\/sw-233276","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T11:32:07Z","timestamp":1685446327000},"page":"777-792","source":"Crossref","is-referenced-by-count":3,"title":["Neural axiom network for knowledge graph reasoning"],"prefix":"10.1177","volume":"15","author":[{"given":"Juan","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, 38 Zheda Rd, Hangzhou, China"}]},{"given":"Xiangnan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, 38 Zheda Rd, Hangzhou, China"}]},{"given":"Hongtao","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, 38 Zheda Rd, Hangzhou, China"}]},{"given":"Jiaoyan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, 15 Parks Rd, Oxford OX1 3QD, UK"}]},{"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, 1689 Jiangnan Rd, Ningbo, China"}]}],"member":"179","reference":[{"key":"10.3233\/SW-233276_ref1","doi-asserted-by":"crossref","unstructured":"K.D.\u00a0Bollacker, C.\u00a0Evans, P.\u00a0Paritosh, T.\u00a0Sturge and J.\u00a0Taylor, Freebase: A collaboratively created graph database for structuring human knowledge, in: SIGMOD Conference, ACM, 2008, pp.\u00a01247\u20131250.","DOI":"10.1145\/1376616.1376746"},{"key":"10.3233\/SW-233276_ref2","unstructured":"A.\u00a0Bordes, N.\u00a0Usunier, A.\u00a0Garc\u00eda-Dur\u00e1n, J.\u00a0Weston and O.\u00a0Yakhnenko, Translating embeddings for modeling multi-relational data, in: NIPS, 2013, pp.\u00a02787\u20132795."},{"key":"10.3233\/SW-233276_ref3","doi-asserted-by":"crossref","unstructured":"A.\u00a0Bordes, J.\u00a0Weston and N.\u00a0Usunier, Open question answering with weakly supervised embedding models, in: ECML\/PKDD (1), Lecture Notes in Computer Science, Vol.\u00a08724, Springer, 2014, pp.\u00a0165\u2013180.","DOI":"10.1007\/978-3-662-44848-9_11"},{"key":"10.3233\/SW-233276_ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2020.100625"},{"key":"10.3233\/SW-233276_ref6","doi-asserted-by":"crossref","unstructured":"T.\u00a0Dettmers, P.\u00a0Minervini, P.\u00a0Stenetorp and S.\u00a0Riedel, Convolutional 2D knowledge graph embeddings, in: AAAI, AAAI Press, 2018, pp.\u00a01811\u20131818.","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"10.3233\/SW-233276_ref7","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.3233\/SW-233276_ref8","doi-asserted-by":"crossref","unstructured":"T.\u00a0Ebisu and R.\u00a0Ichise, TorusE: Knowledge graph embedding on a Lie group, in: AAAI, AAAI Press, 2018, pp.\u00a01819\u20131826.","DOI":"10.1609\/aaai.v32i1.11538"},{"key":"10.3233\/SW-233276_ref9","doi-asserted-by":"crossref","unstructured":"D.\u00a0Fleischhacker and J.\u00a0V\u00f6lker, Inductive learning of disjointness axioms, in: OTM Conferences (2), Lecture Notes in Computer Science, Vol.\u00a07045, Springer, 2011, pp.\u00a0680\u2013697.","DOI":"10.1007\/978-3-642-25106-1_20"},{"issue":"6","key":"10.3233\/SW-233276_ref10","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1007\/s00778-015-0394-1","article-title":"Fast rule mining in ontological knowledge bases with AMIE+","volume":"24","author":"Gal\u00e1rraga","year":"2015","journal-title":"VLDB J."},{"key":"10.3233\/SW-233276_ref11","doi-asserted-by":"crossref","unstructured":"L.A.\u00a0Gal\u00e1rraga, C.\u00a0Teflioudi, K.\u00a0Hose and F.M.\u00a0Suchanek, AMIE: Association rule mining under incomplete evidence in ontological knowledge bases, in: WWW, International World Wide Web Conferences Steering Committee \/ ACM, 2013, pp.\u00a0413\u2013422.","DOI":"10.1145\/2488388.2488425"},{"key":"10.3233\/SW-233276_ref12","doi-asserted-by":"crossref","unstructured":"X.\u00a0Han, S.\u00a0Cao, X.\u00a0Lv, Y.\u00a0Lin, Z.\u00a0Liu, M.\u00a0Sun and J.\u00a0Li, OpenKE: An open toolkit for knowledge embedding, in: EMNLP (Demonstration), Association for Computational Linguistics, 2018, pp.\u00a0139\u2013144.","DOI":"10.18653\/v1\/D18-2024"},{"key":"10.3233\/SW-233276_ref13","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.artint.2012.06.001","article-title":"YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia","volume":"194","author":"Hoffart","year":"2013","journal-title":"Artif. Intell."},{"key":"10.3233\/SW-233276_ref14","doi-asserted-by":"crossref","unstructured":"R.\u00a0Irny and P.S.\u00a0Kumar, Mining inverse and symmetric axioms in linked data, in: JIST, Lecture Notes in Computer Science, Vol.\u00a010675, Springer, 2017, pp.\u00a0215\u2013231.","DOI":"10.1007\/978-3-319-70682-5_14"},{"key":"10.3233\/SW-233276_ref15","doi-asserted-by":"crossref","unstructured":"P.\u00a0Jain, P.\u00a0Kumar, Mausam and S.\u00a0Chakrabarti, Type-sensitive knowledge base inference without explicit type supervision, in: ACL (2), Association for Computational Linguistics, 2018, pp.\u00a075\u201380.","DOI":"10.18653\/v1\/P18-2013"},{"key":"10.3233\/SW-233276_ref16","doi-asserted-by":"crossref","unstructured":"G.\u00a0Ji, S.\u00a0He, L.\u00a0Xu, K.\u00a0Liu and J.\u00a0Zhao, Knowledge graph embedding via dynamic mapping matrix, in: ACL (1), The Association for Computer Linguistics, 2015, pp.\u00a0687\u2013696.","DOI":"10.3115\/v1\/P15-1067"},{"key":"10.3233\/SW-233276_ref17","doi-asserted-by":"crossref","unstructured":"S.\u00a0Jia, Y.\u00a0Xiang, X.\u00a0Chen, K.\u00a0Wang and S.\u00a0E, Triple trustworthiness measurement for knowledge graph, in: WWW, ACM, 2019, pp.\u00a02865\u20132871.","DOI":"10.1145\/3308558.3313586"},{"key":"10.3233\/SW-233276_ref18","unstructured":"D.P.\u00a0Kingma and J.\u00a0Ba, Adam: A method for stochastic optimization, in: ICLR (Poster), 2015."},{"issue":"2","key":"10.3233\/SW-233276_ref19","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3233\/SW-140134","article-title":"DBpedia \u2013 a large-scale, multilingual knowledge base extracted from Wikipedia","volume":"6","author":"Lehmann","year":"2015","journal-title":"Semantic Web"},{"key":"10.3233\/SW-233276_ref20","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Lin, Z.\u00a0Liu, M.\u00a0Sun, Y.\u00a0Liu and X.\u00a0Zhu, Learning entity and relation embeddings for knowledge graph completion, in: AAAI, AAAI Press, 2015, pp.\u00a02181\u20132187.","DOI":"10.1609\/aaai.v29i1.9491"},{"key":"10.3233\/SW-233276_ref21","doi-asserted-by":"crossref","unstructured":"X.\u00a0Lv, L.\u00a0Hou, J.\u00a0Li and Z.\u00a0Liu, Differentiating concepts and instances for knowledge graph embedding, in: EMNLP, Association for Computational Linguistics, 2018, pp.\u00a01971\u20131979.","DOI":"10.18653\/v1\/D18-1222"},{"key":"10.3233\/SW-233276_ref22","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ma, H.\u00a0Gao, T.\u00a0Wu and G.\u00a0Qi, Learning disjointness axioms with association rule mining and its application to inconsistency detection of linked data, in: CSWS, Communications in Computer and Information Science, Vol.\u00a0480, Springer, 2014, pp.\u00a029\u201341.","DOI":"10.1007\/978-3-662-45495-4_3"},{"issue":"5","key":"10.3233\/SW-233276_ref23","doi-asserted-by":"publisher","first-page":"801","DOI":"10.3233\/SW-200369","article-title":"Automatic detection of relation assertion errors and induction of relation constraints","volume":"11","author":"Melo","year":"2020","journal-title":"Semantic Web"},{"issue":"11","key":"10.3233\/SW-233276_ref24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: A lexical database for English","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"key":"10.3233\/SW-233276_ref25","doi-asserted-by":"crossref","unstructured":"D.Q.\u00a0Nguyen, T.D.\u00a0Nguyen, D.Q.\u00a0Nguyen and D.Q.\u00a0Phung, A novel embedding model for knowledge base completion based on convolutional neural network, in: NAACL-HLT (2), Association for Computational Linguistics, 2018, pp.\u00a0327\u2013333.","DOI":"10.18653\/v1\/N18-2053"},{"key":"10.3233\/SW-233276_ref26","doi-asserted-by":"crossref","unstructured":"D.Q.\u00a0Nguyen, T.\u00a0Vu, T.D.\u00a0Nguyen, D.Q.\u00a0Nguyen and D.Q.\u00a0Phung, A capsule network-based embedding model for knowledge graph completion and search personalization, in: NAACL-HLT (1), Association for Computational Linguistics, 2019, pp.\u00a02180\u20132189.","DOI":"10.18653\/v1\/N19-1226"},{"key":"10.3233\/SW-233276_ref27","doi-asserted-by":"crossref","unstructured":"M.\u00a0Nickel, L.\u00a0Rosasco and T.A.\u00a0Poggio, Holographic embeddings of knowledge graphs, in: AAAI, AAAI Press, 2016, pp.\u00a01955\u20131961.","DOI":"10.1609\/aaai.v30i1.10314"},{"issue":"2","key":"10.3233\/SW-233276_ref28","doi-asserted-by":"publisher","first-page":"63","DOI":"10.4018\/ijswis.2014040104","article-title":"Improving the quality of linked data using statistical distributions","volume":"10","author":"Paulheim","year":"2014","journal-title":"Int. J. Semantic Web Inf. Syst."},{"key":"10.3233\/SW-233276_ref29","unstructured":"Z.\u00a0Sun, Z.\u00a0Deng, J.\u00a0Nie and J.\u00a0Tang, RotatE: Knowledge graph embedding by relational rotation in complex space, in: ICLR (Poster), OpenReview.net, 2019."},{"key":"10.3233\/SW-233276_ref30","unstructured":"T.P.\u00a0Tanon, D.\u00a0Vrandecic, S.\u00a0Schaffert, T.\u00a0Steiner and L.\u00a0Pintscher, From freebase to Wikidata: The great migration, in: WWW, ACM, 2016, pp.\u00a01419\u20131428."},{"key":"10.3233\/SW-233276_ref31","doi-asserted-by":"crossref","unstructured":"G.\u00a0T\u00f6pper, M.\u00a0Knuth and H.\u00a0Sack, DBpedia ontology enrichment for inconsistency detection, in: I-SEMANTICS, ACM, 2012, pp.\u00a033\u201340.","DOI":"10.1145\/2362499.2362505"},{"key":"10.3233\/SW-233276_ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4007"},{"key":"10.3233\/SW-233276_ref33","unstructured":"T.\u00a0Trouillon, J.\u00a0Welbl, S.\u00a0Riedel, \u00c9.\u00a0Gaussier and G.\u00a0Bouchard, Complex embeddings for simple link prediction, in: ICML, JMLR Workshop and Conference Proceedings, Vol.\u00a048, JMLR.org, 2016, pp.\u00a02071\u20132080."},{"issue":"12","key":"10.3233\/SW-233276_ref34","doi-asserted-by":"publisher","first-page":"2724","DOI":"10.1109\/TKDE.2017.2754499","article-title":"Knowledge graph embedding: A survey of approaches and applications","volume":"29","author":"Wang","year":"2017","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.3233\/SW-233276_ref35","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, X.\u00a0He, Y.\u00a0Cao, M.\u00a0Liu and T.\u00a0Chua, KGAT: Knowledge graph attention network for recommendation, in: KDD, ACM, 2019, pp.\u00a0950\u2013958.","DOI":"10.1145\/3292500.3330989"},{"key":"10.3233\/SW-233276_ref36","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Wang, J.\u00a0Zhang, J.\u00a0Feng and Z.\u00a0Chen, Knowledge graph embedding by translating on hyperplanes, in: AAAI, AAAI Press, 2014, pp.\u00a01112\u20131119.","DOI":"10.1609\/aaai.v28i1.8870"},{"key":"10.3233\/SW-233276_ref37","doi-asserted-by":"crossref","unstructured":"R.\u00a0West, E.\u00a0Gabrilovich, K.\u00a0Murphy, S.\u00a0Sun, R.\u00a0Gupta and D.\u00a0Lin, Knowledge base completion via search-based question answering, in: WWW, ACM, 2014, pp.\u00a0515\u2013526.","DOI":"10.1145\/2566486.2568032"},{"key":"10.3233\/SW-233276_ref38","doi-asserted-by":"crossref","unstructured":"R.\u00a0Xie, Z.\u00a0Liu, F.\u00a0Lin and L.\u00a0Lin, Does William Shakespeare REALLY write Hamlet? Knowledge representation learning with confidence, in: AAAI, AAAI Press, 2018, pp.\u00a04954\u20134961.","DOI":"10.1609\/aaai.v32i1.11924"},{"key":"10.3233\/SW-233276_ref39","unstructured":"B.\u00a0Yang, W.\u00a0Yih, X.\u00a0He, J.\u00a0Gao and L.\u00a0Deng, Embedding entities and relations for learning and inference in knowledge bases, in: ICLR (Poster), 2015."},{"key":"10.3233\/SW-233276_ref40","unstructured":"F.\u00a0Yang, Z.\u00a0Yang and W.W.\u00a0Cohen, Differentiable learning of logical rules for knowledge base reasoning, in: NIPS, 2017, pp.\u00a02319\u20132328."},{"key":"10.3233\/SW-233276_ref41","doi-asserted-by":"crossref","unstructured":"W.\u00a0Zhang, B.\u00a0Paudel, L.\u00a0Wang, J.\u00a0Chen, H.\u00a0Zhu, W.\u00a0Zhang, A.\u00a0Bernstein and H.\u00a0Chen, Iteratively learning embeddings and rules for knowledge graph reasoning, in: WWW, ACM, 2019, pp.\u00a02366\u20132377.","DOI":"10.1145\/3308558.3313612"},{"key":"10.3233\/SW-233276_ref42","unstructured":"L.\u00a0Zhao, X.\u00a0Zhang, K.\u00a0Wang, Z.\u00a0Feng and Z.\u00a0Wang, Learning ontology axioms over knowledge graphs via representation learning, in: ISWC Satellites, CEUR Workshop Proceedings, Vol.\u00a02456, CEUR-WS.org, 2019, pp.\u00a057\u201360."}],"container-title":["Semantic Web"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/SW-233276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T11:01:27Z","timestamp":1756206087000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/SW-233276"}},"subtitle":[],"editor":[{"given":"Freddy","family":"Lecue","sequence":"additional","affiliation":[{"name":"INRIA, France"}]}],"short-title":[],"issued":{"date-parts":[[2024,5,14]]},"references-count":41,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.3233\/sw-233276","relation":{},"ISSN":["2210-4968","1570-0844"],"issn-type":[{"type":"electronic","value":"2210-4968"},{"type":"print","value":"1570-0844"}],"subject":[],"published":{"date-parts":[[2024,5,14]]}}}