Abstract
Ontological reasoning has great prospects in applications based on domain-specific knowledge graphs (KG). However, it is difficult for existing logic reasoners to quickly perform inference over large-scale assertional boxes (ABoxes) in domain-specific KGs with complex ontologies. To address this challenge, a novel method named the “neural-symbolic ontological reasoner” is proposed. By incorporating neural-symbolic learning into ABox reasoning, a reasoner named the TimGangReasoner (TGR) is built. The TGR synthesizes graph data using an ontology, trains an ABox reasoning network (ABRN) model, and then approximately compiles the logic reasoning process of the ontology (represented by OWL+SWRL) into neural networks (NNs). The ABRN model encodes instances into vectors and then executes parallel vector computations to accelerate ABox reasoning. Experiments conducted on three open-source complex ontologies show that the TGR can achieve high-quality approximate deductive reasoning on ABoxes. The reasoning time consumption of the TGR increases linearly with the increase in the number of assertions, providing better scalability for large-scale ABoxes. Therefore, the TGR is able to reason quickly and accurately on domain-specific KGs that have complex underlying ontologies and contain large-scale ABoxes.
Similar content being viewed by others
Notes
The open-world assumption (OWA) is the assumption that what is not stated is unknown. Both the ontologies represented by OWL and the KGs represented by RDF are based on the OWA. The closed-world assumption (CWA) is the opposite of the OWA; it assumes that what is not currently known is false.
References
Fensel D, Şimşek U, Angele K, Huaman E, Kärle E, Panasiuk O, Toma I, Umbrich J, Wahler A (2020) Knowledge Graphs. Springer, Cham. https://doi.org/10.1007/978-3-030-37439-6
Abu-Salih B (2021) Domain-specific knowledge graphs: A survey. J Netw Comput Appl 185:103076. https://doi.org/10.1016/j.jnca.2021.103076
Noraset T, Lowphansirikul L, Tuarob S (2021) Wabiqa: a wikipedia-based thai question-answering system. Inf Process Manag 58(1):102431. https://doi.org/10.1016/j.ipm.2020.102431
Färber M, Bartscherer F, Menne C, Rettinger A (2018) Linked data quality of dbpedia, freebase, opencyc, wikidata, and yago. Semantic Web 9(1):77–129. https://doi.org/10.3233/SW-170275
Kejriwal M (2019) Domain-specific Knowledge Graph Construction, 1–7. Springer, Cham. https://doi.org/10.1007/978-3-030-12375-8
Wiharja K, Pan JZ, Kollingbaum MJ, Deng Y (2020) Schema aware iterative knowledge graph completion. J Web Sem 65:100616. https://doi.org/10.1016/j.websem.2020.100616
Tang, X., Feng, Z., Xiao, Y., Wang, M., Ye, T., Zhou, Y., Meng, J., Zhang, B., Zhang, D. (2022) Construction and application of an ontology-based domain-specific knowledge graph for petroleum exploration and development. Geosci Front 101426 . https://doi.org/10.1016/j.gsf.2022.101426
Chen X, Jia S, Xiang Y (2020) A review: Knowledge reasoning over knowledge graph. Expert Syst Appl 141:112948. https://doi.org/10.1016/j.eswa.2019.112948
Baader F, Horrocks I, Sattler U (2004) Handbook on Ontologies. Description logics. Springer, Berlin, pp 3–28. https://doi.org/10.1007/978-3-540-24750-0_1
Qin X, Zhang X, Yasin MQ, Wang S, Feng Z, Xiao G (2021) Suma: A partial materialization-based scalable query answering in owl 2 dl. Data Sci Eng 6(2):229–245. https://doi.org/10.1007/s41019-020-00150-0
Alshahrani M, Khan MA, Maddouri O, Kinjo AR, Queralt- Rosinach N, Hoehndorf R (2017) Neuro-symbolic representation learning on biological knowledge graphs. Bioinformatics 33(17):2723–2730. https://doi.org/10.1093/bioinformatics/btx275
Jain N, Tran T.-K, Gad-Elrab MH, Stepanova D (2021) Improving knowledge graph embeddings with ontological reasoning. In: International Semantic Web Conference, Springer pp. 410–426. https://doi.org/10.1007/978-3-030-88361-4_24
Chen H, Luo X (2019) An automatic literature knowledge graph and reasoning network modeling framework based on ontology and natural language processing. Advanced Engineering Informatics 42:100959. https://doi.org/10.1016/j.aei.2019.100959
Kazakov Y, Krötzsch M, Simančík F (2014) The incredible elk. J Autom Reason 53(1):1–61. https://doi.org/10.1007/s10817-013-9296-3
Carral D, Dragoste I, González L, Jacobs C, Krötzsch M, Urbani J (2019) Vlog: A rule engine for knowledge graphs. In: International Semantic Web Conference, Springer, pp. 19–35. https://doi.org/10.1007/978-3-030-30796-7_2
Ji S, Pan S, Cambria E, Marttinen P, Philip SY (2021) A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans Neural Netw Learn Syst 33(2):494–514. https://doi.org/10.1109/TNNLS.2021.3070843
Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. Adv Neural Inform Process Sys 26
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28. https://ojs.aaai.org/index.php/AAAI/article/view/8870
Sirin E, Parsia B, Grau BC, Kalyanpur A, Katz Y (2007) Pellet: A practical owl-dl reasoner. J Web Seman 5(2):51–53. https://doi.org/10.1016/j.websem.2007.03.004
Glimm B, Horrocks I, Motik B, Stoilos G, Wang Z (2014) Hermit: an owl 2 reasoner. J Autom Reason 53(3):245–269. https://doi.org/10.1007/s10817-014-9305-1
Pan JZ, Bobed C, Guclu I, Bobillo F, Kollingbaum MJ, Mena E, Li Y-F (2018) Predicting reasoner performance on abox intensive owl 2 el ontologies. Int J Semant Web Inform Sys 14(1):1–30. https://doi.org/10.4018/IJSWIS.2018010101
Perconti P, Plebe A (2020) Deep learning and cognitive science. Cognition 203:104365. https://doi.org/10.1016/j.cognition.2020.104365
Franklin NT, Norman KA, Ranganath C, Zacks JM, Gershman SJ (2020) Structured event memory: A neuro-symbolic model of event cognition. Psychol Rev 127(3):327. https://doi.org/10.1037/rev0000177
Belle V (2020) Symbolic logic meets machine learning: A brief survey in infinite domains. In: International Conference on Scalable Uncertainty Management, Springer pp. 3–16. https://doi.org/10.1007/978-3-030-58449-8_1
Hitzler P, Bianchi F, Ebrahimi M, Sarker MK (2020) Neural-symbolic integration and the semantic web. Semant Web 11(1):3–11. https://doi.org/10.3233/SW-190368
Ebrahimi M, Eberhart A, Bianchi F, Hitzler P (2021) Towards bridging the neuro-symbolic gap: Deep deductive reasoners. Appl Intell 51(9):6326–6348. https://doi.org/10.1007/s10489-020-02165-6
Sarker MK, Zhou L, Eberhart A, Hitzler P (2021) Neuro-symbolic artificial intelligence. AI Commun 34(3):197–209. https://doi.org/10.3233/AIC-210084
Hitzler P, Eberhart A, Ebrahimi M, Sarker MK, Zhou L (2022) Neurosymbolic approaches in artificial intelligence. Nat Sci Rev 9(6):035. https://doi.org/10.1093/nsr/nwac035
Garcez Ad, Bader S, Bowman H, Lamb LC, de Penning L, Illuminoo B, Poon H, Gerson Zaverucha C (2022) Neural-symbolic learning and reasoning: A survey and interpretation. Neuro-Symbol Art Intell State Art 342:1. https://doi.org/10.3233/FAIA210348
Zhang J, Chen B, Zhang L, Ke X, Ding H (2021) Neural, symbolic and neural-symbolic reasoning on knowledge graphs. AI Open 2:14–35. https://doi.org/10.1016/j.aiopen.2021.03.001
Hitzler P (2021) A review of the semantic web field. Commun ACM 64(2):76–83. https://doi.org/10.1145/3397512
Bansal, I., Tiwari, S., Rivero, C.R (2020): The impact of negative triple generation strategies and anomalies on knowledge graph completion. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 45–54. https://doi.org/10.1145/3340531.3412023
Linjordet T, Balog K (2020) Sanitizing synthetic training data generation for question answering over knowledge graphs. In: Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval, pp. 121–128. https://doi.org/10.1145/3409256.3409836
Chen Y, Kokar MM, Moskal JJ (2020) Rdf object description generator. Int J Web Eng Technol 15(2):140–169. https://doi.org/10.1504/IJWET.2020.109729
Taelman R, Colpaert P, Mannens E, Verborgh R (2019) Generating public transport data based on population distributions for rdf benchmarking. Semant Web 10(2):305–328. https://doi.org/10.3233/SW-180319
Makni B, Hendler J (2019) Deep learning for noise-tolerant rdfs reasoning. Semant Web 10(5):823–862. https://doi.org/10.3233/SW-190363
Kulmanov M, Liu-Wei W, Yan Y, Hoehndorf R (2019) El embeddings: Geometric construction of models for the description logic el++. In: Proceedings of the 28th International Joint Conferences on Artificial Intelligence. https://doi.org/10.48550/arXiv.1902.10499
Kendall EF, McGuinness DL (2019) Ontology engineering. Synth. Lect. Semant. Web Theory Technol 9(1):102. https://doi.org/10.2200/S00834ED1V01Y201802WBE018
Kaiser A, Kroening D, Wahl T (2017) Lost in abstraction: Monotonicity in multi-threaded programs. Inform Comput 252:30–47. https://doi.org/10.1016/j.ic.2016.03.003
Dong T, Cheng Q, Cao B, Shi J (2018) A novel approach to distributed rule matching and multiple firing based on mapreduce. J Database Manag 29(2):62–84. https://doi.org/10.4018/JDM.2018040104
Antoniou G, Batsakis S, Mutharaju R, Pan JZ, Qi G, Tachmazidis I, Urbani J, Zhou Z (2018) A survey of large-scale reasoning on the web of data. The Knowledge Engineering Review 33. https://doi.org/10.1017/S0269888918000255
Sun Z, Deng Z.-H, Nie J.-Y, Tang J (2019) Rotate: Knowledge graph embedding by relational rotation in complex space. In: International Conference on Learning Representations. https://doi.org/10.48550/arXiv.1902.10197
Lu H, Hu H, Lin X (2022) Dense: An enhanced non-commutative representation for knowledge graph embedding with adaptive semantic hierarchy. Neurocomputing 476:115–125. https://doi.org/10.1016/j.neucom.2021.12.079
Che F, Zhang D, Tao J, Niu M, Zhao B (2020) Parame: Regarding neural network parameters as relation embeddings for knowledge graph completion. Proceedings of the AAAI Conference on Artificial Intelligence 34:2774–2781. https://doi.org/10.1609/aaai.v34i03.5665
Dettmers T, Minervini P, Stenetorp P, Riedel S (2018) Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32. https://doi.org/10.1609/aaai.v32i1.11573
Schlichtkrull M, Kipf TN, Bloem P, Berg Rvd, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European Semantic Web Conference, Springer pp. 593–607. https://doi.org/10.1007/978-3-319-93417-4_38
Shen T, Zhang F, Cheng J (2022) A comprehensive overview of knowledge graph completion. Knowl Based Syst 255:109597. https://doi.org/10.1016/j.knosys.2022.109597
Hohenecker P, Lukasiewicz T (2020) Ontology reasoning with deep neural networks. J Artif Intell Res 68:503–540. https://doi.org/10.1613/jair.1.11661
Horridge M, Parsia B, Sattler U (2009) Explaining inconsistencies in owl ontologies. In: International Conference on Scalable Uncertainty Management, Springer pp. 124–137. https://doi.org/10.1007/978-3-642-04388-8_11
Golbreich C (2004) Combining rule and ontology reasoners for the semantic web. In: International Workshop on Rules and Rule Markup Languages for the Semantic Web, Springer pp. 6–22. https://doi.org/10.1007/978-3-540-30504-0_2
Katsumi M, Grüninger M (2015) Using psl to extend and evaluate event ontologies. In: International Symposium on Rules and Rule Markup Languages for the Semantic Web, Springer pp. 225–240. https://doi.org/10.1007/978-3-319-21542-6_15
Batsakis S, Tachmazidis I, Antoniou G (2017) Representing time and space for the semantic web. Int J Artif Intell Tools 26(03):1750015. https://doi.org/10.1142/S0218213017600156
Zese R, Bellodi E, Riguzzi F, Cota G, Lamma E (2018) Tableau reasoning for description logics and its extension to probabilities. Ann Math Artif Intell 82(1):101–130. https://doi.org/10.1007/s10472-016-9529-3
Van Nguyen S, Tran HM, Maleszka M (2021) Geometric modeling: background for processing the 3d objects. Appl Intell 51:6182–6201. https://doi.org/10.1007/s10489-020-02022-6
Liang Y, He F, Zeng X, Luo J (2022) An improved loop subdivision to coordinate the smoothness and the number of faces via multi-objective optimization. Integr Comput Aided Eng 29(1):23–41. https://doi.org/10.3233/ICA-210661
Acknowledgements
Thanks for the support from Research Project under Grants GK20191A010279, GK20191A010296, in part by the National Science Foundation (NSF) of China under Grants 71571186, 61273322.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Li Yao, Zhaoyun Ding and Cheng Zhu contributed equally to this work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhu, X., Liu, B., Yao, L. et al. TGR: Neural-symbolic ontological reasoner for domain-specific knowledge graphs. Appl Intell 53, 23946–23965 (2023). https://doi.org/10.1007/s10489-023-04834-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04834-8