Abstract
As hyper-relational facts continue to proliferate within knowledge graphs, link prediction on binary relations has become inadequate, while link prediction on hyper-relations has emerged as a research hotspot. Existing methods typically employ n-ary tuples, primary triple with auxiliary descriptions, or hypergraphs to represent hyper-relational facts and conduct link prediction. However, medical hyper-relational facts are more intricate and frequently lack multiple components, which presents challenges for current methods in conveying their structure, semantics, and predicting multiple missing elements simultaneously. To address these issues, in this paper, we introduce MHRE, the pioneering link prediction method specifically designed for medical hyper-relational facts. Initially, we represent medical hyper-relational facts as a heterogeneous multi-relational directed graph with hyper-relations at its core to depict both its structure and implicit semantics. Next, we develop a role-aware graph attention mechanism network to acquire distributed vector representations of entities and relations within the graph. Importantly, it fine-tunes the semantic weights of different components within hyper-relational facts by incorporating neighboring nodes and role information through learning. Lastly, we devise a prediction module based on self-attention mechanisms, enabling the simultaneous prediction of multiple missing elements within a medical hyper-relational fact. We conduct experiments using publicly available datasets, such as JF17K, WikiPeople, and their adapted versions, alongside a proprietary medical dataset. We compare MHRE with state-of-the-art baselines and further conduct ablation studies and parameter analysis. The experimental results confirm the efficacy and superiority of MHRE. In a range of benchmark tests involving hyper-relational facts, MHRE consistently outperforms current state-of-the-art methods.
Graphical abstract
Similar content being viewed by others
Data Availability
The JF17K and WikiPeople datasets are publicly available at https://github.com/PaddlePaddle/Research/tree/master/KG/ACL2021_GRAN. The MedCKG dataset is not currently available as a private dataset.
References
Bollacker KD, Evans C, Paritosh PK, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the ACM SIGMOD international conference on management of data, SIGMOD 2008. Vancouver, pp 1247–1250. https://doi.org/10.1145/1376616.1376746. Accessed 10–12 June 2008
Vrandecic D, Krötzsch M (2014) Wikidata: a free collaborative knowledgebase. Commun ACM 57(10):78–85. https://doi.org/10.1145/2629489
Fernández-Torras A, Duran-Frigola M, Bertoni M, Locatelli M, Aloy P (2022) Integrating and formatting biomedical data as pre-calculated knowledge graph embeddings in the bioteque. Nat Commun 13(1):5304. https://doi.org/10.1038/s41467-022-33026-0
Dong X, Gabrilovich E, Heitz G, Horn W, Lao N, Murphy K, Strohmann T, Sun S, Zhang W (2014) Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, pp 601–610
Li P, Wang X, Liang H, Zhang S, Zhang Y, Jiang Y, Tang Y (2022) A fuzzy semantic representation and reasoning model for multiple associative predicates in knowledge graph. Inf Sci 599:208–230. https://doi.org/10.1016/j.ins.2022.03.079
Gomes J, de Mello RC, Ströele V, de Souza JF (2022) A hereditary attentive template-based approach for complex knowledge base question answering systems. Expert Syst Appl 205:117725. https://doi.org/10.1016/j.eswa.2022.117725
Lu L, Wang B, Zhang Z, Liu S, Xu H (2023) Vrkg4rec: virtual relational knowledge graph for recommendation. In: Chua T, Lauw HW, Si L, Terzi E, Tsaparas P (eds) Proceedings of the sixteenth ACM international conference on web search and data mining, WSDM 2023. Singapore, pp 526–534. https://doi.org/10.1145/3539597.3570482
Sun Y, Wang S, Li Y, Feng S, Tian H, Wu H, Wang H (2020) ERNIE 2.0: a continual pre-training framework for language understanding. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020. New York, pp 8968–8975. https://doi.org/10.1609/aaai.v34i05.6428. Accessed 7–12 Feb 2020
Wang P, Chen J, Su L, Wang Z (2023) N-ary relation prediction based on knowledge graphs with important entity detection. Expert Syst Appl 221:119755. https://doi.org/10.1016/j.eswa.2023.119755
Xu Z, Lv Z, Li J, Sun H, Sheng Z (2023) A novel perspective on travel demand prediction considering natural environmental and socioeconomic factors. IEEE Intell Transp Syst Mag 15(1):136–159. https://doi.org/10.1109/MITS.2022.3162901
Yu X, Chu Y, Jiang F, Guo Y, Gong D (2018) Svms classification based two-side cross domain collaborative filtering by inferring intrinsic user and item features. Knowl-Based Syst 141:80–91. https://doi.org/10.1016/j.knosys.2017.11.010
Yu X, Jiang F, Du J, Gong D (2019) A cross-domain collaborative filtering algorithm with expanding user and item features via the latent factor space of auxiliary domains. Pattern Recogn 94:96–109. https://doi.org/10.1016/j.patcog.2019.05.030
Yu X, Peng Q, Xu L, Jiang F, Du J, Gong D (2021) A selective ensemble learning based two-sided cross-domain collaborative filtering algorithm. Inf Process Manag 58(6):102691. https://doi.org/10.1016/j.ipm.2021.102691
Codd EF (1970) A relational model of data for large shared data banks. Commun ACM 13(6):377–387. https://doi.org/10.1145/362384.362685
Wen J, Li J, Mao Y, Chen S, Zhang R (2016) On the representation and embedding of knowledge bases beyond binary relations. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, IJCAI 2016. New York, pp 1300–1307. Accessed 9–15 July 2016
Guan S, Jin X, Wang Y, Cheng X (2019) Link prediction on n-ary relational data. In: The world wide web conference, WWW 2019. San Francisco, pp 583–593. https://doi.org/10.1145/3308558.3313414. Accessed 13–17 May 2019
Brickley D, Guha RV, McBride B (2014) Rdf schema 1.1. W3C recommendation 25(2004–2014):10
Fatemi B, Taslakian P, Vazquez D, Poole D (2023) Knowledge hypergraph embedding meets relational algebra. J Mach Learn Res 24(105):1–34
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the twenty-eighth AAAI conference on artificial intelligence. Québec City, pp 1112–1119. https://doi.org/10.1609/aaai.v28i1.8870. Accessed 27–31 July 2014
Zhang R, Li J, Mei J, Mao Y (2018) Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In: Proceedings of the 2018 world wide web conference on world wide web, WWW 2018. Lyon, pp 1185–1194. https://doi.org/10.1145/3178876.3186017. Accessed 23–27 April 2018
Liu Y, Yao Q, Li Y (2020) Generalizing tensor decomposition for n-ary relational knowledge bases. In: WWW ’20: the web conference 2020. Taipei, pp 1104–1114. https://doi.org/10.1145/3366423.3380188. Accessed 20–24 April 2020
Balazevic I, Allen C, Hospedales TM (2019) Tucker: tensor factorization for knowledge graph completion. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019. Hong Kong, pp 5184–5193. https://doi.org/10.18653/v1/D19-1522. Accessed 3–7 Nov 2019
Di S, Yao Q, Chen L (2021) Searching to sparsify tensor decomposition for n-ary relational data. In: WWW ’21: the web conference 2021, virtual event. Ljubljana, pp 4043–4054. https://doi.org/10.1145/3442381.3449853. Accessed 19–23 April 2021
Liu Y, Yao Q, Li Y (2021) Role-aware modeling for n-ary relational knowledge bases. In: WWW ’21: the web conference 2021, virtual event. Ljubljana, pp 2660–2671. https://doi.org/10.1145/3442381.3449874. Accessed 19–23 April 2021
Huang Y, Sun H, Xu K, Lu S, Wang T, Zhang X (2021) Corelate: learning the correlation in multi-fold relations for knowledge graph embedding. Knowl-Based Syst 213:106601. https://doi.org/10.1016/j.knosys.2020.106601
Zhang Y, Xu H, Zhang X, Wu X, Yang Z (2021) Trfr: a ternary relation link prediction framework on knowledge graphs. Ad Hoc Netw 113:102402. https://doi.org/10.1016/j.adhoc.2020.102402
Rosso P, Yang D, Cudré-Mauroux P (2020) Beyond triplets: hyper-relational knowledge graph embedding for link prediction. In: WWW ’20: the web conference 2020. Taipei, pp 1885–1896. https://doi.org/10.1145/3366423.3380257. Accessed 20–24 April 2020
Guan S, Jin X, Guo J, Wang Y, Cheng X (2020) Neuinfer: knowledge inference on n-ary facts. In: Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, pp 6141–6151. https://doi.org/10.18653/v1/2020.acl-main.546. Accessed 5–10 July 2020
Galkin M, Trivedi P, Maheshwari G, Usbeck R, Lehmann J (2020) Message passing for hyper-relational knowledge graphs. In: Proceedings of the 2020 conference on empirical methods in natural language processing, EMNLP 2020, Online, pp 7346–7359. https://doi.org/10.18653/v1/2020.emnlp-main.596. Accessed 16–20 Nov 2020
Vashishth S, Sanyal S, Nitin V, Talukdar PP (2020) Composition-based multi-relational graph convolutional networks. In: 8th international conference on learning representations, ICLR 2020, Addis Ababa. https://openreview.net/forum?id=BylA C4tPr. 26–30 April 2020
Wang Q, Wang H, Lyu Y, Zhu Y (2021) Link prediction on n-ary relational facts: a graph-based approach. In: Findings of the association for computational linguistics: ACL/IJCNLP 2021, online event, findings of ACL, vol ACL/IJCNLP 2021, pp 396–407. https://doi.org/10.18653/v1/2021.findings-acl.35. Accessed 1–6 Aug 2021
Yan S, Zhang Z, Xu G, Sun X, Li S, Wang S (2022) Modeling n-ary relational data as gyro-polygons with learnable gyro-centroid. Knowl-Based Syst 251:109164. https://doi.org/10.1016/j.knosys.2022.109164
Fatemi B, Taslakian P, Vázquez D, Poole D (2020) Knowledge hypergraphs: Prediction beyond binary relations. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence, IJCAI 2020, pp 2191–2197. https://doi.org/10.24963/ijcai.2020/303
Yan S, Zhang Z, Sun X, Xu G, Jin L, Li S (2022) Hyper2: hyperbolic embedding for hyper-relational link prediction. Neurocomputing 492:440–451. https://doi.org/10.1016/j.neucom.2022.04.026
Yadati N, Nimishakavi M, Yadav P, Nitin V, Louis A, Talukdar PP (2019) Hypergcn: a new method for training graph convolutional networks on hypergraphs. In: Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, NeurIPS 2019. Vancouver, pp 1509–1520. Accessed 8–14 Dec 2019
Ji S, Pan S, Cambria E, Marttinen P, Yu PS (2022) A survey on knowledge graphs: representation, acquisition, and applications. IEEE Trans Neural Networks Learn Syst 33(2):494–514. https://doi.org/10.1109/TNNLS.2021.3070843
Zhang Y, Yao Q, Dai W, Chen L (2020) Autosf: searching scoring functions for knowledge graph embedding. In: 36th IEEE international conference on data engineering, ICDE 2020. Dallas, pp 433–444. https://doi.org/10.1109/ICDE48307.2020.00044. Accessed 20–24 April 2020
Rossi A, Barbosa D, Firmani D, Matinata A, Merialdo P (2021) Knowledge graph embedding for link prediction: a comparative analysis. ACM Trans Knowl Discov Data 15(2):14–11449. https://doi.org/10.1145/3424672
Wang Q, Mao Z, Wang B, Guo L (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Trans Know Data Eng 29(12):2724–2743
Bordes A, Usunier N, García-Durán A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. In: Advances in neural information processing ystems 26: 27th annual conference on neural information processing systems 2013. Proceedings of a meeting held. Lake Tahoe, pp 2787–2795. https://proceedings.neurips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html. Accessed 5–8 Dec 2013
Liu R, Yin G, Liu Z, Zhang L (2023) PTKE: translation-based temporal knowledge graph embedding in polar coordinate system, vol 529, pp 80–91. https://doi.org/10.1016/j.neucom.2023.01.079. https://doi.org/10.1016/j.neucom.2023 01.079
Ji G, He S, Xu L, Liu K, Zhao J (2015) Knowledge graph embedding via dynamic mapping matrix. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (vol1: long papers), pp 687–696
Xiao H, Huang M, Hao Y, Zhu X (2015) Transa: an adaptive approach for knowledge graph embedding. arXiv:1509.05490
Ji G, Liu K, He S, Zhao J (2016) Knowledge graph completion with adaptive sparse transfer matrix. In: Thirtieth AAAI conference on artificial intelligence
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: Twenty-ninth AAAI conference on artificial intelligence
Ding B, Wang Q, Wang B, Guo L (2018) Improving knowledge graph embedding using simple constraints. arXiv:1805.02408
Manabe H, Hayashi K, Shimbo M (2018) Data-dependent learning of symmetric/antisymmetric relations for knowledge base completion. In: Thirty-second AAAI conference on artificial intelligence
Yang B, Yih W-t, He X, Gao J, Deng L (2014) Embedding entities and relations for learning and inference in knowledge bases. arXiv:1412.6575
Trouillon T, Welbl J, Riedel S, Gaussier É, Bouchard G (2016) Complex embeddings for simple link prediction. In: international conference on machine learning, PMLR, pp 2071–2080
Shao P, Zhang D, Yang G, Tao J, Che F, Liu T (2022) Tucker decomposition-based temporal knowledge graph completion. Knowl-Based Syst 238:107841. https://doi.org/10.1016/j.knosys.2021.107841
Yang J, Ying X, Shi Y, Xing B (2024) Tensor decompositions for temporal knowledge graph completion with time perspective. Expert Syst Appl 237:121267. https://doi.org/10.1016/j.eswa.2023.121267
Nguyen DQ, Vu T, Nguyen TD, Nguyen DQ, Phung D (2018) A capsule network-based embedding model for knowledge graph completion and search personalization. arXiv:1808.04122
Yao S, Pi D, Chen J, Xu Y (2022) Gckg: novel gated convolutional embedding model for knowledge graphs. Expert Syst Appl 208:118142. https://doi.org/10.1016/j.eswa.2022.118142
Baghershahi P, Hosseini R, Moradi H (2023) Self-attention presents low-dimensional knowledge graph embeddings for link prediction. Knowl-Based Syst 260:110124. https://doi.org/10.1016/j.knosys.2022.110124
Feng J, Wei Q, Cui J, Chen J (2022) Novel translation knowledge graph completion model based on 2d convolution. Appl Intell 52(3):3266–3275. https://doi.org/10.1007/s10489-021-02438-8
Li Z, Zhao Y, Zhang Y, Zhang Z (2022) Multi-relational graph attention networks for knowledge graph completion. Knowl-Based Syst 251:109262. https://doi.org/10.1016/j.knosys.2022.109262
Dai G, Wang X, Zou X, Liu C, Cen S (2022) Mrgat: multi-relational graph attention network for knowledge graph completion. Neural Netw 154:234–245. https://doi.org/10.1016/j.neunet.2022.07.014
Zhang X, Zhang C, Guo J, Peng C, Niu Z, Wu X (2023) Graph attention network with dynamic representation of relations for knowledge graph completion. Expert Syst Appl 219:119616. https://doi.org/10.1016/j.eswa.2023.119616
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: 5th international conference on learning representations, ICLR 2017. Conference Track Proceedings, Toulon. https://openreview.net/forum?id=SJU4ayYgl. Accessed 24–26 April 2017
Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. In: 6th international conference on learning representations, ICLR 2018. Conference Track Proceedings, Vancouver. https://openreview.net/forum?id=rJXMpikCZ
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30: annual conference on neural information processing systems 2017. Long Beach, pp 5998–6008. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html. Accessed 4–9 Dec 2017
Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies. NAACL-HLT 2019, Minneapolis, MN, USA, vol 1 (long and short papers), pp 4171–4186. https://doi.org/10.18653/v1/n19-1423. Accessed 2–7 June 2019
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015. Conference Track Proceedings, San Diego. Accessed 7–9 May 2015
Acknowledgements
We would like to thank the anonymous reviewers for their insightful suggestions. Our work is supported by the National Key Research and Development Program of China (No.2020AAA0109400).
Author information
Authors and Affiliations
Contributions
Author 1 (First Author) designed the study, performed measurements, designed the analysis, and wrote the manuscript. Author 2 designed the medical schema and extracted the data. Author 3 designed the analysis and the medical schema. Author 4 designed the analysis and the medical schema. Author 5 designed the study and the analysis. Author 6 designed the study and the analysis. All authors contributed to the article and approved the submitted version.
Corresponding author
Ethics declarations
Competing Interests
The authors declare no potential conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A: Hyperparameter settings
We tuned our model on the validation set using the hyperparameters reported in Table 7. Bold values are fixed across all the datasets. The characters in brackets are shorthand for the hyperparameters.
In addition, on each dataset, we further tuned the hyperparameters. As shown in Table 8.
Appendix B: Infrastructure and runtime
We train our MHRE model on one Tesla V100 32G GPU using the hyperparameters selected in Tables 7 and 8. On JF17K, our model takes about 6 hours to train and evaluate. On WikiPeople, it takes about 1.5 days. On \(\text {WikiPeople}^-\), it takes about 22 hours. For JF17K-3, JF17K-4, WikiPeople-3, and WikiPeople-4, the runtime is around 1.5 hours. On JF17K-4+ and WikiPeople-4+, it takes roughly 3 hours. In contrast, running the MHRE model on MedCKG requires approximately 2 days. Because of the effect of parameters and graph convolution, MHRE is weaker than previous methods like GRAN and HINGE in terms of time efficiency, but similar to STARE.
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
Wang, W., Zhang, X., Zhang, J. et al. MHRE: Multivariate link prediction method for medical hyper-relational facts. Appl Intell 54, 1311–1334 (2024). https://doi.org/10.1007/s10489-023-05248-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-05248-2