{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:07:30Z","timestamp":1776881250350,"version":"3.51.2"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["U23B2030, 62272260, and 62171260"],"award-info":[{"award-number":["U23B2030, 62272260, and 62171260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>The binary relational knowledge base (KB, a.k.a. knowledge graph), representing real-world knowledge with binary relations and entities, has been an important research topic in artificial intelligence, while, considerable knowledge also involves beyond-binary relations. Recently, the area proposes to model n-ary relational KBs with both binary and beyond-binary relations included. However, most current models are extended from translational distance and neural network models in binary relational KBs, which suffer from weak expressiveness and high complexity, respectively. To overcome such issues, in this work, we propose a novel two-step modeling framework, GETD, generalizing the powerful tensor decomposition technique from binary relational KBs to the n-ary case. For n-ary relational KBs with single-arity relations, the GETD framework introduces Tucker decomposition and Tensor Ring decomposition for expressive and efficient modeling. Furthermore, the framework is technically extended for the representation of n-ary relational KBs with mixed-arity relations. The existing negative sampling technique is also generalized to the n-ary case for GETD. In addition, we theoretically prove that the GETD framework is fully expressive to completely represent any KBs. Empirical results on two representative datasets show that the proposed framework significantly outperforms the state-of-the-art methods, achieving 11\u201326% and 4\u20137% improvements on Hits@10 for the single-arity and the mixed-arity cases, respectively.<\/jats:p>","DOI":"10.1145\/3709002","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T16:04:41Z","timestamp":1740585881000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Modeling N-ary Relational Knowledge Bases with Tensor Decomposition"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2399-2829","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-8618","authenticated-orcid":false,"given":"Quanming","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology (BNRist), Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,19]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"2623","article-title":"Optuna: A next-generation hyperparameter optimization framework","author":"Akiba Takuya","year":"2019","unstructured":"Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A next-generation hyperparameter optimization framework. In KDD, 2623\u20132631.","journal-title":"KDD"},{"key":"e_1_3_2_3_2","first-page":"5184","article-title":"TuckER: Tensor factorization for knowledge graph completion","author":"Bala\u017eevi\u0107 Ivana","year":"2019","unstructured":"Ivana Bala\u017eevi\u0107, Carl Allen, and Timothy M. Hospedales. 2019. TuckER: Tensor factorization for knowledge graph completion. In EMNLP, 5184\u20135193.","journal-title":"EMNLP"},{"key":"e_1_3_2_4_2","first-page":"1247","article-title":"Freebase: A collaboratively created graph database for structuring human knowledge","author":"Bollacker Kurt","year":"2008","unstructured":"Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A collaboratively created graph database for structuring human knowledge. In SIGMOD, 1247\u20131250.","journal-title":"SIGMOD"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5363-6"},{"key":"e_1_3_2_6_2","unstructured":"Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Irreflexive and hierarchical relations as translations. arXiv:1304.7158. Retrieved from https:\/\/arxiv.org\/abs\/1304.7158"},{"key":"e_1_3_2_7_2","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In NeurIPS, 2787\u20132795.","journal-title":"NeurIPS"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/362384.362685"},{"key":"e_1_3_2_9_2","first-page":"1811","article-title":"Convolutional 2D knowledge graph embeddings","author":"Dettmers Tim","year":"2018","unstructured":"Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2018. Convolutional 2D knowledge graph embeddings. In AAAI, 1811\u20131818.","journal-title":"AAAI"},{"key":"e_1_3_2_10_2","first-page":"4043","article-title":"Searching to sparsify tensor decomposition for N-ary relational data","author":"Di Shimin","year":"2021","unstructured":"Shimin Di, Quanming Yao, and Lei Chen. 2021. Searching to sparsify tensor decomposition for N-ary relational data. In WWW, 4043\u20134054.","journal-title":"WWW"},{"key":"e_1_3_2_11_2","first-page":"1013","article-title":"HighLife: Higher-arity fact harvesting","author":"Ernst Patrick","year":"2018","unstructured":"Patrick Ernst, Amy Siu, and Gerhard Weikum. 2018. HighLife: Higher-arity fact harvesting. In WWW, 1013\u20131022.","journal-title":"WWW"},{"key":"e_1_3_2_12_2","first-page":"2191","article-title":"Knowledge hypergraphs: Prediction beyond binary relations","author":"Fatemi Bahare","year":"2021","unstructured":"Bahare Fatemi, Perouz Taslakian, David Vazquez, and David Poole. 2021. Knowledge hypergraphs: Prediction beyond binary relations, In IJCAI, 2191\u20132197.","journal-title":"IJCAI"},{"key":"e_1_3_2_13_2","first-page":"7346","article-title":"Message passing for hyper-relational knowledge graphs","author":"Galkin Mikhail","year":"2020","unstructured":"Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck, and Jens Lehmann. 2020. Message passing for hyper-relational knowledge graphs. In EMNLP, 7346\u20137359.","journal-title":"EMNLP"},{"key":"e_1_3_2_14_2","first-page":"6141","article-title":"Neuinfer: Knowledge inference on N-ary facts","author":"Guan Saiping","year":"2020","unstructured":"Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, and Xueqi Cheng. 2020. Neuinfer: Knowledge inference on N-ary facts. In ACL, 6141\u20136151.","journal-title":"ACL"},{"key":"e_1_3_2_15_2","first-page":"583","article-title":"Link prediction on N-ary relational data","author":"Guan Saiping","year":"2019","unstructured":"Saiping Guan, Xiaolong Jin, Yuanzhuo Wang, and Xueqi Cheng. 2019. Link prediction on N-ary relational data. In WWW, 583\u2013593.","journal-title":"WWW"},{"key":"e_1_3_2_16_2","unstructured":"V\u00edctor Guti\u00e9rrez-Basulto and Steven Schockaert. 2018. From knowledge graph embedding to ontology embedding? An analysis of the compatibility between vector space representations and rules. arXiv:1805.10461. Retrieved from https:\/\/arxiv.org\/abs\/1805.10461"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/sapm192761164"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106601"},{"key":"e_1_3_2_19_2","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. In ICML, 448\u2013456.","journal-title":"ICML"},{"key":"e_1_3_2_20_2","first-page":"985","article-title":"Knowledge graph completion with adaptive sparse transfer matrix","author":"Ji Guoliang","year":"2016","unstructured":"Guoliang Ji, Kang Liu, Shizhu He, and Jun Zhao. 2016. Knowledge graph completion with adaptive sparse transfer matrix. In AAAI, 985\u2013991.","journal-title":"AAAI"},{"issue":"2","key":"e_1_3_2_21_2","first-page":"494","article-title":"A survey on knowledge graphs: Representation, acquisition and applications","volume":"33","author":"Ji Shaoxiong","year":"2021","unstructured":"Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and S. Yu Philip. 2021. A survey on knowledge graphs: Representation, acquisition and applications. IEEE TNNLS 33, 2 (2021), 494\u2013514.","journal-title":"IEEE TNNLS"},{"key":"e_1_3_2_22_2","unstructured":"Armand Joulin Edouard Grave Piotr Bojanowski Maximilian Nickel and Tomas Mikolov. 2017. Fast linear model for knowledge graph embeddings. arXiv:1710.10881. Retrieved from https:\/\/arxiv.org\/abs\/1710.10881"},{"key":"e_1_3_2_23_2","first-page":"4289","article-title":"Simple embedding for link prediction in knowledge graphs","author":"Kazemi Seyed Mehran","year":"2018","unstructured":"Seyed Mehran Kazemi and David Poole. 2018. Simple embedding for link prediction in knowledge graphs. In NeurIPS, 4289\u20134300.","journal-title":"NeurIPS"},{"key":"e_1_3_2_24_2","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In ICLR, 1\u201315.","journal-title":"ICLR"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"e_1_3_2_26_2","first-page":"2863","article-title":"Canonical tensor decomposition for knowledge base completion","author":"Lacroix Timothee","year":"2018","unstructured":"Timothee Lacroix, Nicolas Usunier, and Guillaume Obozinski. 2018. Canonical tensor decomposition for knowledge base completion. In ICML, 2863\u20132872.","journal-title":"ICML"},{"key":"e_1_3_2_27_2","first-page":"2181","article-title":"Learning entity and relation embeddings for knowledge graph completion","author":"Lin Yankai","year":"2015","unstructured":"Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015. Learning entity and relation embeddings for knowledge graph completion. In AAAI, 2181\u20132187.","journal-title":"AAAI"},{"key":"e_1_3_2_28_2","unstructured":"Yu Liu Shu Yang Jingtao Ding Quanming Yao and Yong Li. 2024. Generalizing hyperedge expansion for hyper-relational knowledge graph modeling. arXiv:2411.06191. Retrieved from https:\/\/arxiv.org\/abs\/2411.06191"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380188"},{"key":"e_1_3_2_30_2","first-page":"1","volume-title":"IJCAI Tensor Network Representations in Machine Learning Workshop","author":"Liu Yu","year":"2020","unstructured":"Yu Liu, Quanming Yao, and Yong Li. 2020. Multiary relational knowledge base completion via tensor decomposition. In IJCAI Tensor Network Representations in Machine Learning Workshop, 1\u20134."},{"key":"e_1_3_2_31_2","first-page":"2660","article-title":"Role-aware modeling for N-ary relational knowledge bases","author":"Liu Yu","year":"2021","unstructured":"Yu Liu, Quanming Yao, and Yong Li. 2021. Role-aware modeling for N-ary relational knowledge bases. In WWW, 2660\u20132671.","journal-title":"WWW"},{"key":"e_1_3_2_32_2","first-page":"5962","article-title":"Barack\u2019s wife Hillary: Using knowledge graphs for fact-aware language modeling","author":"Logan Robert","year":"2019","unstructured":"Robert Logan, Nelson F. Liu, Matthew E. Peters, Matt Gardner, and Sameer Singh. 2019. Barack\u2019s wife Hillary: Using knowledge graphs for fact-aware language modeling. In ACL, 5962\u20135971.","journal-title":"ACL"},{"key":"e_1_3_2_33_2","first-page":"1211","article-title":"Neural network-based question answering over knowledge graphs on word and character level","author":"Lukovnikov Denis","year":"2017","unstructured":"Denis Lukovnikov, Asja Fischer, Jens Lehmann, and S\u00f6ren Auer. 2017. Neural network-based question answering over knowledge graphs on word and character level. In WWW, 1211\u20131220.","journal-title":"WWW"},{"key":"e_1_3_2_34_2","first-page":"11","volume-title":"Proc. IEEE","volume":"104","author":"Nickel Maximilian","year":"2015","unstructured":"Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2015. A review of relational machine learning for knowledge graphs. Proc. IEEE 104, 1 (2015), 11\u201333."},{"key":"e_1_3_2_35_2","first-page":"3104482","article-title":"A three-way model for collective learning on multi-relational data","author":"Nickel Maximilian","year":"2011","unstructured":"Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A three-way model for collective learning on multi-relational data. In ICML, 3104482\u20133104584.","journal-title":"ICML"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014683"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380257"},{"key":"e_1_3_2_38_2","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In ESWC, 593\u2013607.","journal-title":"ESWC"},{"key":"e_1_3_2_39_2","unstructured":"Amit Singhal. 2012. Introducing the knowledge graph: Things not strings. Official Google Blog 5. Rerieved from https:\/\/blog.google\/products\/search\/introducing-knowledge-graph-things-not\/"},{"key":"e_1_3_2_40_2","first-page":"926","article-title":"Reasoning with neural tensor networks for knowledge base completion","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Danqi Chen, Christopher D. Manning, and Andrew Ng. 2013. Reasoning with neural tensor networks for knowledge base completion. In NeurIPS, 926\u2013934.","journal-title":"NeurIPS"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"e_1_3_2_43_2","first-page":"697","article-title":"RotatE: Knowledge graph embedding by relational rotation in complex space","author":"Sun Zhiqing","year":"2018","unstructured":"Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2018. RotatE: Knowledge graph embedding by relational rotation in complex space. In ICLR, 697\u2013706.","journal-title":"ICLR"},{"key":"e_1_3_2_44_2","first-page":"2071","article-title":"Complex embeddings for simple link prediction","author":"Trouillon Th\u00e9o","year":"2016","unstructured":"Th\u00e9o Trouillon, Johannes Welbl, Sebastian Riedel, \u00c9ric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In ICML, 2071\u20132080.","journal-title":"ICML"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"e_1_3_2_46_2","first-page":"1","article-title":"Composition-based multi-relational graph convolutional networks","author":"Vashishth Shikhar","year":"2019","unstructured":"Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, and Partha Talukdar. 2019. Composition-based multi-relational graph convolutional networks. In ICLR, 1\u201315.","journal-title":"ICLR"},{"issue":"10","key":"e_1_3_2_47_2","first-page":"78","article-title":"Wikidata: A free collaborative knowledge base","volume":"57","author":"Vrande\u010di\u0107 Denny","year":"2014","unstructured":"Denny Vrande\u010di\u0107 and Markus Kr\u00f6tzsch. 2014. Wikidata: A free collaborative knowledge base. Commun. ACM 57, 10 (2014), 78\u201385.","journal-title":"Commun."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"e_1_3_2_49_2","first-page":"9329","article-title":"Wide compression: Tensor ring nets","author":"Wang Wenqi","year":"2018","unstructured":"Wenqi Wang, Yifan Sun, Brian Eriksson, Wenlin Wang, and Vaneet Aggarwal. 2018. Wide compression: Tensor ring nets. In CVPR, 9329\u20139338.","journal-title":"CVPR"},{"key":"e_1_3_2_50_2","first-page":"4227","article-title":"On multi-relational link prediction with bilinear models","author":"Wang Yanjie","year":"2018","unstructured":"Yanjie Wang, Rainer Gemulla, and Hui Li. 2018. On multi-relational link prediction with bilinear models. In AAAI, 4227\u20134234.","journal-title":"AAAI"},{"key":"e_1_3_2_51_2","first-page":"1112","article-title":"Knowledge graph embedding by translating on hyperplanes","author":"Wang Zhen","year":"2014","unstructured":"Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge graph embedding by translating on hyperplanes. In AAAI, 1112\u20131119.","journal-title":"AAAI"},{"key":"e_1_3_2_52_2","first-page":"1300","article-title":"On the representation and embedding of knowledge bases beyond binary relations","author":"Wen Jianfeng","year":"2016","unstructured":"Jianfeng Wen, Jianxin Li, Yongyi Mao, Shini Chen, and Richong Zhang. 2016. On the representation and embedding of knowledge bases beyond binary relations. In IJCAI, 1300\u20131307.","journal-title":"IJCAI"},{"key":"e_1_3_2_53_2","first-page":"1","article-title":"Embedding entities and relations for learning and inference in knowledge bases","author":"Yang Bishan","year":"2015","unstructured":"Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In ICLR, 1\u201312.","journal-title":"ICLR"},{"key":"e_1_3_2_54_2","first-page":"353","article-title":"Collaborative knowledge base embedding for recommender systems","author":"Zhang Fuzheng","year":"2016","unstructured":"Fuzheng Zhang, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma. 2016. Collaborative knowledge base embedding for recommender systems. In SIGKDD, 353\u2013362.","journal-title":"SIGKDD"},{"key":"e_1_3_2_55_2","first-page":"1185","article-title":"Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding","author":"Zhang Richong","year":"2018","unstructured":"Richong Zhang, Junpeng Li, Jiajie Mei, and Yongyi Mao. 2018. Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In WWW, 1185\u20131194.","journal-title":"WWW"},{"key":"e_1_3_2_56_2","unstructured":"Qibin Zhao Guoxu Zhou Shengli Xie Liqing Zhang and Andrzej Cichocki. 2016. Tensor ring decomposition. arXiv:1606.05535. Retrieved from https:\/\/arxiv.org\/abs\/1606.05535"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709002","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3709002"],"URL":"https:\/\/doi.org\/10.1145\/3709002","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,19]]},"assertion":[{"value":"2022-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}