Abstract
Graph neural networks (GNNs) are an extension of deep neural networks based on graph data, and have been widely used in various fields. However, due to the disadvantages of the existing GNN architecture, GNN is limited in many fields. Therefore, a large number of researchers have devoted their energy to the optimization of GNN. In this work, we provide a comprehensive survey of graph-structure optimization methods involving GNNs in various problems, and show the recent optimization methods comprehensively. We compare the literature on the basis of the taxonomy of the optimization direction, optimization effect and algorithm itself. Finally, we discuss several future research directions and related open problems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, Y., Gu, K., Sun, Y., Wang, W.: Bi-level graph neural networks for drug-drug interaction prediction. arXiv:2006.14002 (2020)
Creamer, R.: Beet curly top virus transmission, epidemiology, and management. In: Applied Plant Virology, pp. 521–527. Elsevier (2020). https://doi.org/10.1016/B978-0-12-818654-1.00037-2
Portugal, P.P., Vilca, G.V.: Methods and systems for providing graphical representations of relationships between customers and computing objects. US9552136 (2017)
Panagopoulos, G., Nikolentzos, G., Vazirgiannis, M.: United we stand: transfer graph neural networks for pandemic forecasting. arXiv:2009.08388 (2020)
Li, Z., Shen, X., Jiao, Y., Pan, X., Bu, J.: Hierarchical bipartite graph neural networks: towards large-scale e-commerce applications. In: 2020 IEEE 36th International Conference on Data Engineering (ICDE). IEEE (2020)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Networks 20(1), 61 (2009)
Lecun, Y., Bengio, Y.: Convolutional networks for images, speech, and time-series. Handbook of Brain Theory & Neural Networks (1995)
Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, vol. 38. IEEE (2013)
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Sig. Process. Magaz. 34(4), 18–42 (2017). https://doi.org/10.1109/MSP.2017.2693418
Zha, Z.J., Tao, M., Wang, J., Wang, Z., Hua, X.S.: Graph-based semi-supervised learning with multi-label. IEEE (2008)
Wan, S., Pan, S., Yang, J., Gong, C.: Contrastive and generative graph convolutional networks for graph-based semi-supervised learning. arXiv:2009.07111 (2020)
Wang, X., Bo, D., Shi, C., Fan, S., Ye, Y., Yu, P.S.: A survey on heterogeneous graph embedding: methods, techniques, applications and sources. arXiv:2011.14867 (2020)
Hu, B., Fang, Y., Shi, C.: Adversarial learning on heterogeneous information networks. In: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019). ACM (2019)
Zhao, J., Wang, X., Shi, C., Hu, B., Song, G., Ye, Y.: Heterogeneous Graph Structure Learning for Graph Neural Networks. AAAIÂ 2021 (2020)
Mcpherson, M., Cook, S.: Birds of a feather: homophily in social networks. Ann. Rev. Sociol. 27, 415–444 (2001)
Zhu, J., Rossi, R.A., Rao, A., Mai, T., Lipka, N., Ahmed, N.K., et al.: Graph neural networks with heterophily. In: AAAI Conference on Artificial Intelligence, 12 May 2021, vol. 35, pp. 11168–11176 (2020)
Xian, X., Fang, L., Sun, S.: REGNN: a repeat aware graph neural network for session-based recommendations. IEEE Access 99, 1–1 (2020)
Sankar, A., Liu, Y., Yu, J., & Shah, N.: Graph Neural Networks for Friend Ranking in Large-scale Social Platforms. WWW 2021: The Web Conference 2021 (2021)
Bochkovskiy, A., Wang, C.Y., Liao, H.: Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934 (2020)
Menon, S., Damian, A., Hu, S., Ravi, N., Rudin, C.: Pulse: self-supervised photo upsampling via latent space exploration of generative models. IEEE (2020)
Ye, J., Zhao, J., Ye, K., Xu, C.: How to build a graph-based deep learning architecture in traffic domain: a survey. IEEE Trans. Intell. Transp. Syst. (2020). https://doi.org/10.1109/TITS.2020.3043250
Roy, A., Roy, K.K., Ali, A.A., Amin, M.A., Rahman, A.: SST-GNN: simplified spatio-temporal traffic forecasting model using graph neural network. arXiv:2104.00055 (2021)
Acknowledgement
This work is supported in part by Natural Science Foundation of China under Grant No. 62106081, Natural Science Foundation of Hubei Province under Grant 2021CFB139 and Project 2662020XXQD002 supported by the Fundamental Research Funds for the Central Universities.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, J., Liu, Y., Chen, Y., Wang, Y. (2022). Recent Graph Neural Networks: A Survey. In: Liu, Q., Liu, X., Cheng, J., Shen, T., Tian, Y. (eds) Proceedings of the 12th International Conference on Computer Engineering and Networks. CENet 2022. Lecture Notes in Electrical Engineering, vol 961. Springer, Singapore. https://doi.org/10.1007/978-981-19-6901-0_155
Download citation
DOI: https://doi.org/10.1007/978-981-19-6901-0_155
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6900-3
Online ISBN: 978-981-19-6901-0
eBook Packages: Computer ScienceComputer Science (R0)