Abstract
Knowledge graph embedding (KGE) projects entities and relations into low-dimension continuous vector space, which promotes the widespread use of knowledge graphs in many downstream applications. Despite the fact that most of existing KGE models focus on static single-modal knowledge graphs, many knowledge graphs are incremental and multi-modal in the real world. Especially, the incremental entities are accompanied by new modalities, i.e., unseen modalities in background knowledge graphs. To well address the novel task, i.e., incrementally embed the new entities with unseen modal information effectively and efficiently, we propose a novel incremental multi-modal knowledge graph embedding model entitled Multi-Modal Rotating on Hyperplanes, which consists of the following two modules. (1) To gain a high-quality background KGE space, the module Background Knowledge Graph Embedding Module is developed to fuse seen modal information with a gated multi-modal encoder and decode the triples by a rotation-based KGE model. (2) The module Incremental Knowledge Graph Embedding Module is designed to fuse unseen modal information of incremental entities and incrementally embed the new entities into the trained embedding space. Extensive experiments are conducted on two real-world multi-modal datasets, and the results demonstrate the superiority of the proposed model in terms of both effectiveness and efficiency compared with the state-of-the-art approaches.
Similar content being viewed by others
Availability of data and materials
The datasets WN9-IMG and FB-IMG in the experiments are public datasets.
References
Sun Z, Yang J, Zhang J, Bozzon A, Huang L, Xu C (2018) Recurrent knowledge graph embedding for effective recommendation. In: RecSys, pp 297–305
Cui L, Lee D (2022) KETCH: knowledge graph enhanced thread recommendation in healthcare forums. In: SIGIR, pp 492–501
Joshi U, Urbani J (2020) Searching for embeddings in a haystack: link prediction on knowledge graphs with subgraph pruning. In: WWW, pp 2817–2823
Shi Y, Cheng G, Kharlamov E (2020) Keyword search over knowledge graphs via static and dynamic hub labelings. In: WWW, pp 235–245
Halliwell N (2022) Evaluating explanations of relational graph convolutional network link predictions on knowledge graphs. In: AAAI, pp 12880–12881
Chen J, He H, Wu F, Wang J (2021) Topology-aware correlations between relations for inductive link prediction in knowledge graphs. In: AAAI, pp 6271–6278
Wang Q, Mao Z, Wang B, Guo L (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Trans Knowl 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: NIPS, pp 2787–2795
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: AAAI, pp 1112–1119
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: AAAI, pp 2181–2187
Yang B, Yih W, He X, Gao J, Deng L (2015) Embedding entities and relations for learning and inference in knowledge bases. In: ICLR, pp 1–12
Trouillon T, Welbl J, Riedel S, Gaussier É, Bouchard G (2016) Complex embeddings for simple link prediction. In: ICML, vol. 48, pp. 2071–2080
Dettmers T, Minervini P, Stenetorp P, Riedel S (2018) Convolutional 2D knowledge graph embeddings. In: AAAI, pp 1811–1818
Che F, Zhang D, Tao J, Niu M, Zhao B (2020) ParamE: regarding neural network parameters as relation embeddings for knowledge graph completion. In: AAAI, pp 2774–2781
Zhang Z, Cai J, Zhang Y, Wang J (2020) Learning hierarchy-aware knowledge graph embeddings for link prediction. In: AAAI, pp 3065–3072
Ley M (2009) DBLP—some lessons learned. Proc VLDB Endow 2(2):1493–1500
Dong L, Zhao D, Zhang X, Li X, Kang X, Yao H (2021) Anchors-based incremental embedding for growing knowledge graphs. IEEE Trans Knowl Data Eng 1(1):1–13
Wei Y, Chen W, Li Z, Zhao L (2021) Incremental update of knowledge graph embedding by rotating on hyperplanes. In: ICWS, pp 516–524
Fei L, Wu T, Khan A (2021) Online updates of knowledge graph embedding. In: Complex networks, vol 1016, pp 523–535
Xie R, Liu Z, Luan H, Sun M (2017) Image-embodied knowledge representation learning. In: IJCAI, pp 3140–3146
Sergieh H.M, Botschen T, Gurevych I, Roth S (2018) A multimodal translation-based approach for knowledge graph representation learning. In: NAACL, pp 225–234
Hori C, Hori T, Lee T, Zhang Z, Harsham B, Hershey JR, Marks TK, Sumi K (2017) Attention-based multimodal fusion for video description. In: ICCV, pp 4203–4212
Ji G, Liu K, He S, Zhao J (2016) Knowledge graph completion with adaptive sparse transfer matrix. In: AAAI, pp 985–991
He S, Liu K, Ji G, Zhao J (2015) Learning to represent knowledge graphs with gaussian embedding. In: CIKM, pp 623–632
Qian W, Fu C, Zhu Y, Cai D, He X (2018) Translating embeddings for knowledge graph completion with relation attention mechanism. In: IJCAI, pp 4286–4292
Yang S, Tian J, Zhang H, Yan J, He H, Jin Y (2019) TransMS: knowledge graph embedding for complex relations by multidirectional semantics. In: IJCAI, pp 1935–1942
Sun Z, Deng Z, Nie J, Tang J (2019) Rotate: knowledge graph embedding by relational rotation in complex space. In: ICLR, pp 1–12
Tay Y, Luu AT, Hui S.C (2017) Non-parametric estimation of multiple embeddings for link prediction on dynamic knowledge graphs. In: AAAI, pp 1243–1249
Wu T, Khan A, Gao H, Li C (2019) Efficiently embedding dynamic knowledge graphs. arXiv:1910.06708
Jia Y, Wang Y, Jin X, Lin H, Cheng X (2018) Knowledge graph embedding: a locally and temporally adaptive translation-based approach. ACM Trans Web 12(2):1–33
Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: EMNLP, pp 1532–1543
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: ICLR, pp 1–14
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: ICLR, pp 1–15
Acknowledgements
This work was supported by the Major Program of the Natural Science Foundation of Jiangsu Higher Education Institutions of China under Grant No. 19KJA610002, the National Natural Science Foundation of China under Grant Nos. 61902270 and No. 62272332, and the Ningbo Science and Technology Special Project with Grant No. 2021Z019.
Funding
The funding concludes the Major Program of the Natural Science Foundation of Jiangsu Higher Education Institutions of China under Grant No. 19KJA610002, the National Natural Science Foundation of China under Grant Nos. 61902270 and 62272332, and the Ningbo Science and Technology Special Project with Grant No. 2021Z019.
Ethics declarations
Conflict of interest
We declare that we have no conflict of interest.
Ethical approval and consent to participate
Not applicable.
Human and animal rights
Not applicable.
Consent for publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Wei, Y., Chen, W., Wen, S. et al. Knowledge graph incremental embedding for unseen modalities. Knowl Inf Syst 65, 3611–3631 (2023). https://doi.org/10.1007/s10115-023-01868-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-01868-9