{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T23:22:35Z","timestamp":1783120955302,"version":"3.54.6"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V050869\/1"],"award-info":[{"award-number":["EP\/V050869\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P025943\/1"],"award-info":[{"award-number":["EP\/P025943\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.artint.2026.104545","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:05:59Z","timestamp":1777043159000},"page":"104545","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["From monotonic graph neural networks to datalog and back: Expressive power and practical applications"],"prefix":"10.1016","volume":"357","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9847-4949","authenticated-orcid":false,"given":"David","family":"Tena Cucala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernardo","family":"Cuenca Grau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2506-4118","authenticated-orcid":false,"given":"Boris","family":"Motik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8886-6129","authenticated-orcid":false,"given":"Egor V.","family":"Kostylev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2026.104545_bib0001","series-title":"Proc. of the 29tnh AAAI Conf. on Artificial Intelligence (AAAI 2015)","first-page":"2181","article-title":"Learning entity and relation embeddings for knowledge graph completion","author":"Lin","year":"2015"},{"key":"10.1016\/j.artint.2026.104545_bib0002","series-title":"Proc. of the 21st Int. Semantic Web Conf. (ISWC 2022)","first-page":"592","article-title":"The DLCC node classification benchmark for analyzing knowledge graph embeddings","author":"Portisch","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0003","series-title":"Proc. of the 26th Int. Conf. on World Wide Web (WWW 2017)","first-page":"1211","article-title":"Neural network-based question answering over knowledge graphs on word and character level","author":"Lukovnikov","year":"2017"},{"key":"10.1016\/j.artint.2026.104545_bib0004","series-title":"Proc. of the 25th ACM SIGKDD Int. Conf. on Knowledge Discovery & Data Mining (KDD 2019)","first-page":"950","article-title":"KGAT: knowledge graph attention network for recommendation","author":"Wang","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0005","series-title":"Foundations of Databases","author":"Abiteboul","year":"1995"},{"issue":"1","key":"10.1016\/j.artint.2026.104545_bib0006","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/A:1008376514077","article-title":"Approximating the semantics of logic programs by recurrent neural networks","volume":"11","author":"H\u00f6lldobler","year":"1999","journal-title":"Appl. Intell."},{"key":"10.1016\/j.artint.2026.104545_bib0007","series-title":"Proc. of the 18th Int. Florida Artificial Intelligence Research Society Conference (FLAIRS 2005)","first-page":"314","article-title":"Computing first-order logic programs by fibring artificial neural networks","author":"Bader","year":"2005"},{"key":"10.1016\/j.artint.2026.104545_bib0008","series-title":"Proc. of the 20th Int. Joint Conf. on Artificial Intelligence (IJCAI 2007)","first-page":"666","article-title":"A fully connectionist model generator for covered first-order logic programs","author":"Bader","year":"2007"},{"key":"10.1016\/j.artint.2026.104545_bib0009","series-title":"Proc. of the 7th Int. Conf. on Learning Representations (ICLR 2019)","article-title":"Neural logic machines","author":"Dong","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0010","unstructured":"A. Campero, A. Pareja, T. Klinger, J. Tenenbaum, S. Riedel, Logical Rule Induction and Theory Learning Using Neural Theorem Proving, (2018). arXiv:abs\/1809.02193."},{"key":"10.1016\/j.artint.2026.104545_bib0011","series-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)","first-page":"3788","article-title":"End-to-end differentiable proving","author":"Rockt\u00e4schel","year":"2017"},{"key":"10.1016\/j.artint.2026.104545_bib0012","series-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)","first-page":"2319","article-title":"Differentiable learning of logical rules for knowledge base reasoning","author":"Yang","year":"2017"},{"key":"10.1016\/j.artint.2026.104545_bib0013","series-title":"Advances in Neural Information Processing Systems 32 (NeurIPS 2019)","first-page":"15321","article-title":"DRUM: end-to-end differentiable rule mining on knowledge graphs","author":"Sadeghian","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0014","series-title":"Graph Neural Networks: Foundations, Frontiers, and Applications","author":"Wu","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0015","series-title":"Proc. of the 15th Int. Semantic Web Conf. (ISWC 2018)","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","volume":"10843","author":"Schlichtkrull","year":"2018"},{"key":"10.1016\/j.artint.2026.104545_bib0016","series-title":"Proc. of the 21st Int. Semantic Web Conference (ISWC 2022)","first-page":"481","article-title":"GNNQ: a neuro-symbolic approach to query answering over incomplete knowledge graphs","volume":"13489","author":"Pflueger","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0017","series-title":"Advances in Neural Information Processing Systems 34 (NeurIPS 2021)","first-page":"2034","article-title":"INDIGO: GNN-based inductive knowledge graph completion using pair-wise encoding","author":"Liu","year":"2021"},{"key":"10.1016\/j.artint.2026.104545_bib0018","series-title":"Proc. of the 2019 IEEE Int. Conference on Acoustics, Speech and Signal Processing (ICASSP 2019)","first-page":"8157","article-title":"A recurrent graph neural network for multi-relational data","author":"Ioannidis","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0019","series-title":"Proc. of the 36th Int. Conf. on Machine Learning (ICML 2019)","first-page":"5241","article-title":"GMNN: graph Markov neural networks","volume":"97","author":"Qu","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0020","series-title":"Proc. of the 33rd Int. Conf. on Machine Learning (ICML 2016)","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume":"48","author":"Yang","year":"2016"},{"key":"10.1016\/j.artint.2026.104545_bib0021","series-title":"Proc. of the 5th Int. Conf. on Learning Representations (ICLR 2017)","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.artint.2026.104545_bib0022","series-title":"Advances in Neural Information Processing Systems 31 (NeurIPS 2018)","first-page":"5171","article-title":"Link prediction based on graph neural networks","author":"Zhang","year":"2018"},{"key":"10.1016\/j.artint.2026.104545_bib0023","series-title":"Proc. of the 37th Int. Conf. on Machine Learning (ICML 2020)","first-page":"9448","article-title":"Inductive relation prediction by subgraph reasoning","volume":"119","author":"Teru","year":"2020"},{"issue":"3","key":"10.1016\/j.artint.2026.104545_bib0024","doi-asserted-by":"crossref","first-page":"16:1","DOI":"10.1145\/1567274.1567278","article-title":"Semantics and complexity of SPARQL","volume":"34","author":"P\u00e9rez","year":"2009","journal-title":"ACM Trans. Database Syst."},{"key":"10.1016\/j.artint.2026.104545_bib0025","unstructured":"B. Motik, B. Cuenca Grau, I. Horrocks, Z. Wu, A. Fokoue, C. Lutz, OWL 2 Web Ontology Language: Profiles (2nd Edition), 2012, W3C Recommendation, https:\/\/www.w3.org\/TR\/2012\/REC-owl2-profiles-20121211\/."},{"key":"10.1016\/j.artint.2026.104545_bib0026","series-title":"Proc. of the 8th Int. Conf. on Learning Representations (ICLR 2020)","article-title":"The logical expressiveness of graph neural networks","author":"Barcel\u00f3","year":"2020"},{"key":"10.1016\/j.artint.2026.104545_bib0027","article-title":"The Description Logic Handbook: Theory, Implementation and Applications","year":"2007"},{"key":"10.1016\/j.artint.2026.104545_bib0028","series-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)","article-title":"A theory of link prediction via relational Weisfeiler-Leman","author":"Huang","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0029","series-title":"Proc. of the 38th Annual ACM\/IEEE Symposium on Logic in Computer Science (LICS 2023)","first-page":"1","article-title":"The descriptive complexity of graph neural networks","author":"Grohe","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0030","series-title":"Proc. of the the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019)","first-page":"4602","article-title":"Weisfeiler and Leman go neural: higher-order graph neural networks","author":"Morris","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0031","series-title":"7th International Conference on Learning Representations","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019"},{"issue":"7","key":"10.1016\/j.artint.2026.104545_bib0032","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1007\/s10994-021-06017-3","article-title":"Beyond graph neural networks with lifted relational neural networks","volume":"110","author":"Sourek","year":"2021","journal-title":"Mach. Learn."},{"key":"10.1016\/j.artint.2026.104545_bib0033","series-title":"Proc. of the 51st Int. Colloquium on Automata, Languages, and Programming (ICALP 2024)","first-page":"127:1","article-title":"Decidability of graph neural networks via logical characterizations","volume":"297","author":"Benedikt","year":"2024"},{"key":"10.1016\/j.artint.2026.104545_bib0034","series-title":"Proc. of the 20th Int. Conf. on Principles of Knowledge Representation and Reasoning (KR 2023)","first-page":"658","article-title":"On the correspondence between monotonic max-sum GNNs and datalog","author":"Tena Cucala","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0035","series-title":"Proc. of the 10th Int. Conf. on Learning Representations (ICLR 2022)","article-title":"Explainable GNN-based models over knowledge graphs","author":"Tena Cucala","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0036","series-title":"Advances in Neural Information Processing Systems 26 (NIPS 2013)","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"10.1016\/j.artint.2026.104545_bib0037","series-title":"Proc. of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)","first-page":"564","article-title":"DeepPath: a reinforcement learning method for knowledge graph reasoning","author":"Xiong","year":"2017"},{"key":"10.1016\/j.artint.2026.104545_bib0038","series-title":"Proc. of the 32nd AAAI Conf. on Artificial Intelligence (AAAI 2018)","first-page":"1811","article-title":"Convolutional 2D knowledge graph embeddings","author":"Dettmers","year":"2018"},{"key":"10.1016\/j.artint.2026.104545_bib0039","series-title":"Proc. of the 12th Int. Conf. on Learning Representations (ICLR 2024)","article-title":"Faithful rule extraction for differentiable rule learning models","author":"Wang","year":"2024"},{"key":"10.1016\/j.artint.2026.104545_bib0040","series-title":"Proc. of the 28th Int. Joint Conf. on Artificial Intelligence (IJCAI 2019)","first-page":"3137","article-title":"Anytime bottom-up rule learning for knowledge graph completion","author":"Meilicke","year":"2019"},{"issue":"6","key":"10.1016\/j.artint.2026.104545_bib0041","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0950-7051(96)81920-4","article-title":"Survey and critique of techniques for extracting rules from trained artificial neural networks","volume":"8","author":"Andrews","year":"1995","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.artint.2026.104545_bib0042","series-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)","first-page":"3517","article-title":"Learning rule-induced subgraph representations for inductive relation prediction","author":"Liu","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0043","series-title":"Proc. of the 9th Int. Conf. on Learning Representations (ICLR 2021)","article-title":"RNNLogic: learning logic rules for reasoning on knowledge graphs","author":"Qu","year":"2021"},{"key":"10.1016\/j.artint.2026.104545_bib0044","series-title":"Proc. of the 8th Int. Conf. on Learning Representations (ICLR 2020)","article-title":"Differentiable learning of numerical rules in knowledge graphs","author":"Wang","year":"2020"},{"key":"10.1016\/j.artint.2026.104545_bib0045","series-title":"Proc. of the 6th Int. Conf. on Learning Representations (ICLR 2018)","article-title":"Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning","author":"Das","year":"2018"},{"key":"10.1016\/j.artint.2026.104545_bib0046","series-title":"Proc. of the 27th Int. Joint Conf. on Artificial Intelligence (IJCAI 2018)","first-page":"2149","article-title":"Scalable rule learning via learning representation","author":"Omran","year":"2018"},{"key":"10.1016\/j.artint.2026.104545_bib0047","series-title":"Proc. of the 28th Int. World Wide Web Conf. (WWW 2019)","first-page":"2366","article-title":"Iteratively learning embeddings and rules for knowledge graph reasoning","author":"W","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0048","series-title":"Proc. of the 19th Int. Conf. on Principles of Knowledge Representation and Reasoning (KR 2022)","article-title":"Looking inside the black-box: logic-based explanations for neural networks","author":"Ferreira","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0049","series-title":"Proc. of the 19th Int. Conf. on Principles of Knowledge Representation and Reasoning (KR 2022)","first-page":"484","article-title":"Faithful approaches to rule learning","author":"Tena Cucala","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0050","series-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)","first-page":"2981","article-title":"Deep lattice networks and partial monotonic functions","author":"You","year":"2017"},{"issue":"109","key":"10.1016\/j.artint.2026.104545_bib0051","first-page":"1","article-title":"Monotonic calibrated interpolated look-up tables","volume":"17","author":"Gupta","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2026.104545_bib0052","series-title":"Advances in Neural Information Processing Systems 32 (NeurIPS 2019)","first-page":"1543","article-title":"Unconstrained monotonic neural networks","author":"Wehenkel","year":"2019"},{"issue":"6","key":"10.1016\/j.artint.2026.104545_bib0053","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."},{"issue":"2","key":"10.1016\/j.artint.2026.104545_bib0054","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3371315","article-title":"Mining expressive rules in knowledge graphs","volume":"12","author":"Ahmadi","year":"2020","journal-title":"ACM J. Data Inf. Qual."},{"key":"10.1016\/j.artint.2026.104545_bib0055","unstructured":"Y. Gu, Y. Guan, P. Missier, Efficient Rule Learning with Template Saturation for Knowledge Graph Completion, (2020). arXiv:abs\/2003.06071."},{"issue":"4","key":"10.1016\/j.artint.2026.104545_bib0056","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/BF03037089","article-title":"Inductive logic programming","volume":"8","author":"Muggleton","year":"1991","journal-title":"New Gener. Comput."},{"key":"10.1016\/j.artint.2026.104545_bib0057","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1613\/jair.1.13507","article-title":"Inductive logic programming at 30: a new introduction","volume":"74","author":"Cropper","year":"2022","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.artint.2026.104545_bib0058","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.5714","article-title":"Learning explanatory rules from noisy data","volume":"61","author":"Evans","year":"2018","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.artint.2026.104545_bib0059","series-title":"Proc. of the 24th Int. Conf. on Inductive Logic Programming (ILP 2014)","first-page":"62","article-title":"Logical minimisation of meta-rules within meta-interpretive learning","volume":"9046","author":"Cropper","year":"2014"},{"key":"10.1016\/j.artint.2026.104545_bib0060","series-title":"Proc. of the 28th Int. Joint Conf. on Artificial Intelligence (IJCAI 2019)","first-page":"6117","article-title":"Synthesizing datalog programs using numerical relaxation","author":"Si","year":"2019"},{"issue":"62","key":"10.1016\/j.artint.2026.104545_bib0061","first-page":"1","article-title":"Provenance-guided synthesis of datalog programs","volume":"4","author":"Raghothaman","year":"2020","journal-title":"ACM Program. Lang."},{"key":"10.1016\/j.artint.2026.104545_bib0062","series-title":"Advances in Neural Information Processing Systems 32 (NeurIPS 2019)","first-page":"9240","article-title":"GNNExplainer: generating explanations for graph neural networks","author":"Ying","year":"2019"},{"key":"10.1016\/j.artint.2026.104545_bib0063","series-title":"Advances in Neural Information Processing Systems 33 (NeurIPS 2020)","article-title":"Parameterized explainer for graph neural network","author":"Luo","year":"2020"},{"key":"10.1016\/j.artint.2026.104545_bib0064","series-title":"Proc. of the 38th Int. Conf. on Machine Learning (ICML 2021)","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume":"139","author":"Lin","year":"2021"},{"key":"10.1016\/j.artint.2026.104545_bib0065","series-title":"Proc. of the 11th Int. Conf. on Learning Representations (ICLR 2023)","article-title":"Fundamental limits in formal verification of message-passing neural networks","author":"S\u00e4lzer","year":"2023"},{"key":"10.1016\/j.artint.2026.104545_bib0066","series-title":"Proc. of the 38th AAAI Conf. on Artificial Intelligence (AAAI 2024)","article-title":"Recurrent graph neural networks and their connections to bisimulation and logic","author":"Pflueger","year":"2024"},{"key":"10.1016\/j.artint.2026.104545_bib0067","unstructured":"P. Nunn, M. S\u00e4lzer, F. Schwarzentruber, N. Troquard, A Logic for Reasoning About Aggregate-Combine Graph Neural Networks, (2024). arXiv:abs\/2405.00205."},{"key":"10.1016\/j.artint.2026.104545_bib0068","series-title":"The 10th Int. Conf. on Learning Representations (ICLR 2022)","article-title":"Expressiveness and approximation properties of graph neural networks","author":"Geerts","year":"2022"},{"key":"10.1016\/j.artint.2026.104545_bib0069","series-title":"Proc. of the 32nd Int. Joint Conf. on Artificial Intelligence (IJCAI 2013)","first-page":"4172","article-title":"Some might say all you need is sum","author":"Rosenbluth","year":"2023"}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226000718?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226000718?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T22:58:21Z","timestamp":1783119501000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370226000718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":69,"alternative-id":["S0004370226000718"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2026.104545","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From monotonic graph neural networks to datalog and back: Expressive power and practical applications","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2026.104545","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104545"}}