Abstract
Heterogeneous graph neural network (HGNN) has drawn considerable research attention in recent years. Knowledge graphs contain hundreds of distinct relations, showing the intrinsic property of strong heterogeneity. However, the majority of HGNNs characterize the heterogeneities by learning separate parameters for different types of nodes and edges in latent space. The number of type-related parameters will be explosively increased when HGNNs attempt to process knowledge graphs, making HGNNs only applicable for graphs with fewer edge types. In this work, to overcome such limitation, we propose a novel heterogeneous graph neural network incorporated with hypernetworks that generate the required parameters by modeling the general semantics among relations. Specifically, we exploit hypernetworks to generate relation-specific parameters of a convolution-based message function to improve the model’s performance while maintaining parameter efficiency. The empirical study on the most commonly-used knowledge base embedding datasets confirms the effectiveness and efficiency of the proposed model. Furthermore, the model parameters have been shown to be significantly reduced (from 415M to 3M on FB15k-237 and from 13M to 4M on WN18RR).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balažević, I., Allen, C., Hospedales, T.M.: Hypernetwork knowledge graph embeddings. In: Proceedings of the ICANN, Munich, Germany, pp. 553–565 (2019). https://doi.org/10.1007/978-3-030-30493-5_52
Bansal, T., Juan, D.C., Ravi, S., McCallum, A.: A2N: attending to neighbors for knowledge graph inference. In: Proceedings of the ACL, Florence, Italy, pp. 4387–4392 (2019). https://doi.org/10.18653/v1/P19-1431
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the SIGMOD, Vancouver, BC, Canada, pp. 1247–1250 (2008). https://doi.org/10.1145/1376616.1376746
Bordes, A., Chopra, S., Weston, J.: Question answering with subgraph embeddings. In: Proceedings of the EMNLP, Doha, Qatar, pp. 615–620 (2014). https://doi.org/10.3115/v1/D14-1067
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of the NIPS, Lake Tahoe, Nevada, United States, pp. 2787–2795 (2013)
Cao, Z., Xu, Q., Yang, Z., Cao, X., Huang, Q.: Dual quaternion knowledge graph embeddings. In: Proceedings of the AAAI, pp. 6894–6902 (2021)
Das, R., et al.: Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning. In: Proceedings of the ICLR, Vancouver, BC, Canada (2018)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: Proceedings of the AAAI, New Orleans, Louisiana, USA, pp. 1811–1818 (2018). https://doi.org/10.1609/aaai.v32i1.11573
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the NAACL-HIT, Minneapolis, Minnesota, pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/n19-1423
Dong, X., et al.: Knowledge vault: a web-scale approach to probabilistic knowledge fusion. In: Proceedings of the SIGKDD, New York, NY, USA, pp. 601–610 (2014). https://doi.org/10.1145/2623330.2623623
Färber, M., Bartscherer, F., Menne, C., Rettinger, A.: Linked data quality of DBpedia, freebase, OpenCyc, Wikidata, and YAGO. Semant. Web 9(1), 77–129 (2018). https://doi.org/10.3233/SW-170275
Fu, X., Zhang, J., Meng, Z., King, I.: MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of the WWW, New York, NY, USA, pp. 2331–2341 (2020). https://doi.org/10.1145/3366423.3380297
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Proceedings of the ICML, ICML 2017, pp. 1263–1272. JMLR.org (2017)
Guo, L., Sun, Z., Hu, W.: Learning to exploit long-term relational dependencies in knowledge graphs. In: Proceedings of the ICML, Long Beach, California, USA, vol. 97, pp. 2505–2514 (2019)
Ha, D., Dai, A., Le, Q.V.: Hypernetworks. In: Proceedings of the ICLR, Toulon, France (2017)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the NIPS, pp. 1025–1035. Curran Associates Inc., Red Hook (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, Las Vegas, NV, USA, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Hu, Z., Dong, Y., Wang, K., Sun, Y.: Heterogeneous graph transformer. In: Proceedings of the Web Conference 2020, New York, NY, USA, pp. 2704–2710 (2020). https://doi.org/10.1145/3366423.3380027
Huang, Z., Li, X., Ye, Y., Ng, M.K.: MR-GCN: multi-relational graph convolutional networks based on generalized tensor product. In: Proceedings of the IJCAI, pp. 1258–1264 (2020). https://doi.org/10.24963/ijcai.2020/175
Jia, C., Shen, Y., Tang, Y., Sun, L., Lu, W.: Heterogeneous graph neural networks for concept prerequisite relation learning in educational data. In: Proceedings of the NAACL-HIT, pp. 2036–2047 (2021). https://doi.org/10.18653/v1/2021.naacl-main.164
Jia, X., De Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: Proceedings of the NIPS, Red Hook, NY, USA, vol. 29 (2016)
Jiang, X., Wang, Q., Wang, B.: Adaptive convolution for multi-relational learning. In: Proceedings of the NAACL-HIT, Minneapolis, Minnesota, pp. 978–987 (2019). https://doi.org/10.18653/v1/N19-1103
Jin, D., Huo, C., Liang, C., Yang, L.: Heterogeneous graph neural network via attribute completion. In: Proceedings of the Web Conference 2021, pp. 391–400. Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3442381.3449914
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the ICLR, San Diego, CA, USA (2015)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the ICLR, Toulon, France (2017)
Lehmann, J., et al.: DBpedia-a large-scale, multilingual knowledge base extracted from Wikipedia. Semant. Web 6(2), 167–195 (2015). https://doi.org/10.3233/SW-140134
Li, Z., Liu, H., Zhang, Z., Liu, T., Xiong, N.N.: Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Trans. Neural Netw. Learn. Syst. 1–13 (2021). https://doi.org/10.1109/TNNLS.2021.3055147
Liu, Z., Fang, Y., Liu, C., Hoi, S.C.H.: Node-wise localization of graph neural networks. In: Proceedings of the IJCAI, Montreal, Canada, pp. 1520–1526 (2021). https://doi.org/10.24963/ijcai.2021/210
Ma, Y., Crook, P.A., Sarikaya, R., Fosler-Lussier, E.: Knowledge graph inference for spoken dialog systems. In: Proceedings of the ICASSP, South Brisbane, Queensland, Australia, pp. 5346–5350 (2015). https://doi.org/10.1109/ICASSP.2015.7178992
Nachmani, E., Wolf, L.: Hyper-graph-network decoders for block codes. In: Proceedings of the NIPS, Vancouver, BC, Canada, pp. 2326–2336 (2019)
Nachmani, E., Wolf, L.: Molecule property prediction and classification with graph hypernetworks. Computing Research Repository arXiv:2002.00240 (2020)
Nathani, D., Chauhan, J., Sharma, C., Kaul, M.: Learning attention-based embeddings for relation prediction in knowledge graphs. In: Proceedings of the ACL, pp. 4710–4723. Florence, Italy (2019). https://doi.org/10.18653/v1/P19-1466
Nguyen, D.Q., Nguyen, T.D., Nguyen, D.Q., Phung, D.: A novel embedding model for knowledge base completion based on convolutional neural network. In: Proceedings of the NAACL-HIT, New Orleans, Louisiana, pp. 327–333 (2018). https://doi.org/10.18653/v1/N18-2053
Nguyen, D.Q., Vu, T., Nguyen, T.D., Nguyen, D.Q., Phung, D.: A capsule network-based embedding model for knowledge graph completion and search personalization. In: Proceedings of the NAACL-HIT, Minneapolis, Minnesota, pp. 2180–2189 (2019). https://doi.org/10.18653/v1/N19-1226
Nickel, M., Tresp, V., Kriegel, H.P.: A three-way model for collective learning on multi-relational data. In: Proceedings of the ICML, Bellevue, Washington, USA, pp. 809–816 (2011)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Proceedings of the NIPS, Vancouver, BC, Canada, pp. 8024–8035 (2019)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)
Riegler, G., Schulter, S., Rüther, M., Bischof, H.: Conditioned regression models for non-blind single image super-resolution. In: Proceedings of the ICCV, Santiago, Chile, pp. 522–530 (2015). https://doi.org/10.1109/ICCV.2015.67
Ruffinelli, D., Broscheit, S., Gemulla, R.: You can teach an old dog new tricks! on training knowledge graph embeddings. In: Proceedings of the ICLR, Addis Ababa, Ethiopia (2020)
Schlichtkrull, M.S., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: Proceedings of the ESWC, Heraklion, Crete, Greece, vol. 10843, pp. 593–607 (2018). https://doi.org/10.1007/978-3-319-93417-4_38
Shang, C., Tang, Y., Huang, J., Bi, J., He, X., Zhou, B.: End-to-end structure-aware convolutional networks for knowledge base completion. In: Proceedings of the AAAI, Honolulu, Hawaii, USA, vol. 33, pp. 3060–3067 (2019). https://doi.org/10.1609/aaai.v33i01.33013060
Stoica, G., Stretcu, O., Platanios, E.A., Mitchell, T.M., Póczos, B.: Contextual parameter generation for knowledge graph link prediction. In: Proceedings of the AAAI, New York, NY, USA, pp. 3000–3008 (2020). https://doi.org/10.1609/aaai.v34i03.5693
Sun, Z., Vashishth, S., Sanyal, S., Talukdar, P., Yang, Y.: A re-evaluation of knowledge graph completion methods. In: Proceedings of the ACL, pp. 5516–5522 (2020). https://doi.org/10.18653/v1/2020.acl-main.489
Toutanova, K., Chen, D.: Observed versus latent features for knowledge base and text inference. In: Proceedings of the 3rd Workshop on CVSC, Beijing, China, pp. 57–66 (2015). https://doi.org/10.18653/v1/W15-4007
Vashishth, S., Sanyal, S., Nitin, V., Agrawal, N., Talukdar, P.P.: Interacte: improving convolution-based knowledge graph embeddings by increasing feature interactions. In: Proceedings of the AAAI, New York, NK, USA, pp. 3009–3016 (2020). https://doi.org/10.1609/aaai.v34i03.5694
Vashishth, S., Sanyal, S., Nitin, V., Talukdar, P.P.: Composition-based multi-relational graph convolutional networks. In: Proceedings of the ICLR, Addis Ababa, Ethiopia (2020)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: Proceedings of the ICLR, Vancouver, BC, Canada (2018)
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014)
Wang, P., Agarwal, K., Ham, C., Choudhury, S., Reddy, C.K.: Self-supervised learning of contextual embeddings for link prediction in heterogeneous networks. In: Leskovec, J., Grobelnik, M., Najork, M., Tang, J., Zia, L. (eds.) Proceedings of the Web Conference 2021, pp. 2946–2957. ACM/IW3C2, Virtual Event (2021). https://doi.org/10.1145/3442381.3450060
Wang, X., et al.: Heterogeneous graph attention network. In: Proceedings of the WWW, San Francisco, CA, USA, pp. 2022–2032 (2019). https://doi.org/10.1145/3308558.3313562
Wang, Z., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI, Québec City, Québec, Canada, pp. 1112–1119 (2014). https://doi.org/10.1609/aaai.v28i1.8870
Xie, Z., Zhou, G., Liu, J., Huang, J.X.: ReInceptionE: relation-aware inception network with joint local-global structural information for knowledge graph embedding. In: Proceedings of the ACL, pp. 5929–5939 (2020). https://doi.org/10.18653/v1/2020.acl-main.526
Yang, B., Yih, W.t., He, X., Gao, J., Deng, L.: Embedding entities and relations for learning and inference in knowledge bases. In: Proceedings of the ICLR, San Diego, CA, USA (2015)
Ye, R., Li, X., Fang, Y., Zang, H., Wang, M.: A vectorized relational graph convolutional network for multi-relational network alignment. In: Proceedings of the IJCAI, Macao, China, pp. 4135–4141 (2019). https://doi.org/10.24963/ijcai.2019/574
Zhang, C., Song, D., Huang, C., Swami, A., Chawla, N.V.: Heterogeneous graph neural network. In: Proceedings of the SIGKDD, New York, NY, USA, pp. 793–803 (2019). https://doi.org/10.1145/3292500.3330961
Zhang, F., Yuan, N.J., Lian, D., Xie, X., Ma, W.Y.: Collaborative knowledge base embedding for recommender systems. In: Proceedings of the SIGKDD, New York, NY, USA, pp. 353–362 (2016). https://doi.org/10.1145/2939672.2939673
Zhao, J., Wang, X., Shi, C., Hu, B., Song, G., Ye, Y.: Heterogeneous graph structure learning for graph neural networks. In: Proceedings of the AAAI, pp. 4697–4705. AAAI Press (2021)
Zhu, J.-Z., Jia, Y.-T., Xu, J., Qiao, J.-Z., Cheng, X.-Q.: Modeling the correlations of relations for knowledge graph embedding. J. Comput. Sci. Technol. 33(2), 323–334 (2018). https://doi.org/10.1007/s11390-018-1821-8
Acknowledgements
This work was supported by the National Key Research and Development Program of China under Grant 2021YFB3500700.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Zhu, T., Tan, H., Zhang, R. (2022). Heterogeneous Graph Neural Network with Hypernetworks for Knowledge Graph Embedding. In: Sattler, U., et al. The Semantic Web – ISWC 2022. ISWC 2022. Lecture Notes in Computer Science, vol 13489. Springer, Cham. https://doi.org/10.1007/978-3-031-19433-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-19433-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19432-0
Online ISBN: 978-3-031-19433-7
eBook Packages: Computer ScienceComputer Science (R0)