{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T13:19:24Z","timestamp":1777987164890,"version":"3.51.4"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2023YFB2903904"],"award-info":[{"award-number":["2023YFB2903904"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2025A03J4491"],"award-info":[{"award-number":["2025A03J4491"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92270106"],"award-info":[{"award-number":["92270106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["4242039"],"award-info":[{"award-number":["4242039"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2024QN11X088"],"award-info":[{"award-number":["2024QN11X088"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2025A1515010304"],"award-info":[{"award-number":["2025A1515010304"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004826","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":[[2026,6]]},"DOI":"10.1016\/j.artint.2026.104520","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:38:59Z","timestamp":1773938339000},"page":"104520","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Neural knowledge graph reasoning with relational digraph"],"prefix":"10.1016","volume":"355","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2085-7418","authenticated-orcid":false,"given":"Yongqi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5202-4950","authenticated-orcid":false,"given":"Haiquan","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5686-4606","authenticated-orcid":false,"given":"Shuzhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1448-9945","authenticated-orcid":false,"given":"Enjun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-8618","authenticated-orcid":false,"given":"Quanming","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2026.104520_bib0001","series-title":"Technical Report","article-title":"Relational Inductive Biases, Deep Learning, and Graph Networks","author":"Battaglia","year":"2018"},{"issue":"4","key":"10.1016\/j.artint.2026.104520_bib0002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447772","article-title":"Knowledge graphs","volume":"54","author":"Hogan","year":"2021","journal-title":"CSUR"},{"key":"10.1016\/j.artint.2026.104520_bib0003","series-title":"The WebConf","first-page":"151","article-title":"Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences","author":"Cao","year":"2019"},{"key":"10.1016\/j.artint.2026.104520_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2019.112948","article-title":"A review: knowledge reasoning over knowledge graph","volume":"141","author":"Chen","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.artint.2026.104520_bib0005","series-title":"NeurIPS","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes","year":"2013"},{"key":"10.1016\/j.artint.2026.104520_bib0006","series-title":"AAAI","article-title":"Convolutional 2D knowledge graph embeddings","author":"Dettmers","year":"2017"},{"key":"10.1016\/j.artint.2026.104520_bib0007","series-title":"NeurIPS","article-title":"Simple embedding for link prediction in knowledge graphs","volume":"31","author":"Kazemi","year":"2018"},{"key":"10.1016\/j.artint.2026.104520_bib0008","series-title":"EMNLP","first-page":"564","article-title":"DeepPath: a reinforcement learning method for knowledge graph reasoning","author":"Xiong","year":"2017"},{"key":"10.1016\/j.artint.2026.104520_bib0009","series-title":"ICLR","article-title":"Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning","author":"Das","year":"2017"},{"key":"10.1016\/j.artint.2026.104520_bib0010","series-title":"NeurIPS","first-page":"15347","article-title":"DRUM: end-to-end differentiable rule mining on knowledge graphs","author":"Sadeghian","year":"2019"},{"key":"10.1016\/j.artint.2026.104520_bib0011","series-title":"ICLR","article-title":"RNNLogic: learning logic rules for reasoning on knowledge graphs","author":"Qu","year":"2021"},{"key":"10.1016\/j.artint.2026.104520_bib0012","series-title":"ICML","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"10.1016\/j.artint.2026.104520_bib0013","series-title":"ICLR","article-title":"Dynamically pruned message passing networks for large-scale knowledge graph reasoning","author":"Xu","year":"2019"},{"issue":"02","key":"10.1016\/j.artint.2026.104520_bib0014","first-page":"1283","article-title":"CogKR: cognitive graph for multi-hop knowledge reasoning","volume":"35","author":"Du","year":"2023","journal-title":"IEEE TKDE"},{"key":"10.1016\/j.artint.2026.104520_bib0015","series-title":"ICML","article-title":"Inductive relation prediction by subgraph reasoning","author":"Teru","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0016","series-title":"NeurIPS","article-title":"Neural Bellman-ford networks: a general graph neural network framework for link prediction","author":"Zhu","year":"2021"},{"key":"10.1016\/j.artint.2026.104520_bib0017","series-title":"The WebConf","first-page":"912","article-title":"Knowledge graph reasoning with relational digraph","author":"Zhang","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0018","article-title":"ICEWS coded event data","volume":"12","author":"Boschee","year":"2015","journal-title":"Harvard Dataverse"},{"key":"10.1016\/j.artint.2026.104520_bib0019","series-title":"AAAI","first-page":"4732","article-title":"Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks","volume":"35","author":"Zhu","year":"2021"},{"key":"10.1016\/j.artint.2026.104520_bib0020","series-title":"EMNLP","article-title":"Recurrent event network: autoregressive structure inference over temporal knowledge graphs","author":"Jin","year":"2019"},{"key":"10.1016\/j.artint.2026.104520_bib0021","series-title":"SIGKDD","article-title":"T-GAP: learning to walk across time for temporal knowledge graph completion","author":"Jung","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0022","series-title":"NeurIPS","first-page":"2319","article-title":"Differentiable learning of logical rules for knowledge base reasoning","author":"Yang","year":"2017"},{"key":"10.1016\/j.artint.2026.104520_bib0023","unstructured":"B. Yang, W.-t. Yih, X. He, J. Gao, L. Deng, Embedding entities and relations for learning and inference in knowledge bases,(2014), arXiv preprint arXiv:1412.6575."},{"issue":"1","key":"10.1016\/j.artint.2026.104520_bib0024","first-page":"4735","article-title":"Knowledge graph completion via complex tensor factorization","volume":"18","author":"Trouillon","year":"2017","journal-title":"JMLR"},{"key":"10.1016\/j.artint.2026.104520_bib0025","series-title":"ICLR","article-title":"RotatE: knowledge graph embedding by relational rotation in complex space","author":"Sun","year":"2019"},{"key":"10.1016\/j.artint.2026.104520_bib0026","series-title":"ICML","first-page":"13209","article-title":"House: knowledge graph embedding with householder parameterization","author":"Li","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0027","series-title":"ACL","first-page":"6947","article-title":"Compounding geometric operations for knowledge graph completion","author":"Ge","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0028","series-title":"ACL","first-page":"1982","article-title":"Learning low-dimensional multi-domain knowledge graph embedding via dual archimedean spirals","author":"Li","year":"2024"},{"key":"10.1016\/j.artint.2026.104520_bib0029","series-title":"ISWC","first-page":"3","article-title":"Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion","author":"Meilicke","year":"2018"},{"key":"10.1016\/j.artint.2026.104520_bib0030","series-title":"SIGKDD","first-page":"179","article-title":"RLogic: recursive logical rule learning from knowledge graphs","author":"Cheng","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0031","series-title":"ACL","first-page":"4578","article-title":"LATENTLOGIC: learning logic rules in latent space over knowledge graphs","author":"Liu","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0032","series-title":"ESWC","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018"},{"key":"10.1016\/j.artint.2026.104520_bib0033","series-title":"ICLR","article-title":"Composition-based multi-relational graph convolutional networks","author":"Vashishth","year":"2019"},{"key":"10.1016\/j.artint.2026.104520_bib0034","series-title":"AAAI","first-page":"4294","article-title":"Communicative message passing for inductive relation reasoning","author":"Mai","year":"2021"},{"key":"10.1016\/j.artint.2026.104520_bib0035","series-title":"EMNLP","article-title":"Learning sequence encoders for temporal knowledge graph completion","author":"Garc\u00eda-Dur\u00e1n","year":"2018"},{"key":"10.1016\/j.artint.2026.104520_bib0036","series-title":"EMNLP","first-page":"2350","article-title":"Encoding temporal information for time-aware link prediction","author":"Jiang","year":"2016"},{"key":"10.1016\/j.artint.2026.104520_bib0037","series-title":"ICLR","article-title":"Tensor decompositions for temporal knowledge base completion","author":"Lacroix","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0038","series-title":"AAAI","first-page":"3988","article-title":"Diachronic embedding for temporal knowledge graph completion","volume":"34","author":"Goel","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0039","series-title":"CIKM","first-page":"2529","article-title":"Along the time: timeline-traced embedding for temporal knowledge graph completion","author":"Zhang","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0040","series-title":"EMNLP","first-page":"5730","article-title":"TeMP: temporal message passing for temporal knowledge graph completion","author":"Wu","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0041","series-title":"ICLR","article-title":"Explainable subgraph reasoning for fore-casting on temporal knowledge graphs","author":"Han","year":"2021"},{"key":"10.1016\/j.artint.2026.104520_bib0042","series-title":"ACL","first-page":"290","article-title":"Complex evolutional pattern learning for temporal knowledge graph reasoning","author":"Li","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0043","series-title":"IJCAI","first-page":"2152","article-title":"TiRGN: time-guided recurrent graph network with local-global historical patterns for temporal knowledge graph reasoning","author":"Li","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0044","doi-asserted-by":"crossref","unstructured":"Z. Wang, H. Du, Q. Yao, X. Li, Search to pass messages for temporal knowledge graph completion,(2022), arXiv preprint arXiv:2210.16740.","DOI":"10.18653\/v1\/2022.findings-emnlp.458"},{"issue":"10","key":"10.1016\/j.artint.2026.104520_bib0045","first-page":"14018","article-title":"QDN: a quadruplet distributor network for temporal knowledge graph completion","volume":"35","author":"Wang","year":"2023","journal-title":"IEEE TNNLS"},{"key":"10.1016\/j.artint.2026.104520_bib0046","series-title":"ACL","first-page":"3825","article-title":"SiMFy: a simple yet effective approach for temporal knowledge graph reasoning","author":"Liu","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0047","series-title":"ICDE","first-page":"1","article-title":"RETIA: relation-entity twin-interact aggregation for temporal knowledge graph extrapolation","author":"Liu","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0048","series-title":"AAAI","first-page":"4765","article-title":"Temporal knowledge graph reasoning with historical contrastive learning","author":"Xu","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0049","series-title":"Graph Drawing: Algorithms for the Visualization of Graphs","author":"Battista","year":"1998"},{"key":"10.1016\/j.artint.2026.104520_bib0050","series-title":"ICLR","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"10.1016\/j.artint.2026.104520_bib0051","series-title":"Technical Report","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.artint.2026.104520_bib0052","series-title":"NeurIPS","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume":"35","author":"Gorishniy","year":"2022"},{"key":"10.1016\/j.artint.2026.104520_bib0053","series-title":"ICML","first-page":"18796","article-title":"InGram: inductive knowledge graph embedding via relation graphs","author":"Lee","year":"2023"},{"key":"10.1016\/j.artint.2026.104520_bib0054","series-title":"ICLR","article-title":"Towards foundation models for knowledge graph reasoning","author":"Galkin","year":"2024"},{"key":"10.1016\/j.artint.2026.104520_bib0055","series-title":"ICML","first-page":"433","article-title":"Statistical predicate invention","author":"Kok","year":"2007"},{"key":"10.1016\/j.artint.2026.104520_bib0056","series-title":"PWCVSMC","first-page":"57","article-title":"Observed versus latent features for knowledge base and text inference","author":"Toutanova","year":"2015"},{"key":"10.1016\/j.artint.2026.104520_bib0057","series-title":"7th Biennial Conference on Innovative Data Systems Research","article-title":"Yago3: a knowledge base from multilingual wikipedias","author":"Mahdisoltani","year":"2014"},{"issue":"11","key":"10.1016\/j.artint.2026.104520_bib0058","doi-asserted-by":"crossref","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":"10.1016\/j.artint.2026.104520_bib0059","series-title":"AAAI","first-page":"4120","article-title":"TLogic: temporal logical rules for explainable link forecasting on temporal knowledge graphs","volume":"36","author":"Liu","year":"2022"},{"issue":"2","key":"10.1016\/j.artint.2026.104520_bib0060","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1023\/A:1005245900406","article-title":"A note on graded modal logic","volume":"64","author":"De Rijke","year":"2000","journal-title":"Stud. Log."},{"key":"10.1016\/j.artint.2026.104520_bib0061","unstructured":"M. Otto, Graded modal logic and counting bisimulation,(2019), arXiv preprint arXiv:1910.00039."},{"key":"10.1016\/j.artint.2026.104520_bib0062","series-title":"ICLR","article-title":"The logical expressiveness of graph neural networks","author":"Barcel\u00f3","year":"2020"},{"key":"10.1016\/j.artint.2026.104520_bib0063","series-title":"LoG","first-page":"46-1","article-title":"Weisfeiler and leman go relational","author":"Barcelo","year":"2022"}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226000469?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226000469?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:24:09Z","timestamp":1777983849000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370226000469"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":63,"alternative-id":["S0004370226000469"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2026.104520","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Neural knowledge graph reasoning with relational digraph","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2026.104520","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104520"}}