Abstract
Most state-of-the-art Graph Neural Networks focus on node features in the learning process but ignore edge features. However, edge features also contain essential information in real-world, such as financial graphs. Node-centric approaches are suboptimal in edge-sensitive graphs since edge features are not adequately utilized. To address this problem, we present the Edge-Featured Graph Attention Network (EGAT) to leverage edge features in the graph feature representation. Our model is based on the edge-integrated attention mechanism, where both node and edge features are included in the calculation of the message and attention weights. In addition, the importance of edge information suggests that the edge features should be updated to learn high-level representation. So we perform edge updating with the integration of the features of connected nodes. In contrast to edge-node switching, our model acquires the adjacent edge features with the node-transit strategy, avoiding significant lift of computational complexity. Then we employ a multi-scale merge strategy, which concatenates features of every layer to construct hierarchical representation. Moreover, our model can be adapted to domain-specific graph neural networks, which further extends the application scenarios. Experiments show that our model achieves or matches the state-of-the-art on both node-sensitive and edge-sensitive datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhou, J., et al.: Graph neural networks: a review of methods and applications. arXiv e-prints arXiv:1812.08434, December 2018
Zhang, Z., Cui, P., Zhu, W.: Deep learning on graphs: a survey. arXiv e-prints arXiv:1812.04202, December 2018
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv e-prints arXiv:1609.02907, September 2016
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=rJXMpikCZ, accepted as poster
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5998–6008. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf
Yang, Z., Cohen, W.W., Salakhutdinov, R.: Revisiting semi-supervised learning with graph embeddings. In: Balcan, M., Weinberger, K.Q. (eds.) Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, 19–24 June 2016. JMLR Workshop and Conference Proceedings, vol. 48, pp. 40–48. JMLR.org (2016). http://proceedings.mlr.press/v48/yanga16.html
Weber, M., et al.: Scalable graph learning for anti-money laundering: a first look. arXiv e-prints arXiv:1812.00076, November 2018
Xiao, W., et al.: Heterogeneous graph attention network. WWW (2019)
Schlichtkrull, M., Kipf, T.N., Bloem, P., Berg, R.v.d., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. arXiv preprint arXiv:1703.06103 (2017)
Gong, L., Cheng, Q.: Exploiting edge features in graph neural networks. arXiv e-prints arXiv:1809.02709, September 2018
Jiang, X., Ji, P., Li, S.: CensNet: convolution with edge-node switching in graph neural networks. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 2656–2662. International Joint Conferences on Artificial Intelligence Organization, July 2019. https://doi.org/10.24963/ijcai.2019/369
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. arXiv e-prints arXiv:1704.01212, April 2017
Lu, C., Liu, Q., Wang, C., Huang, Z., Lin, P., He, L.: Molecular property prediction: a multilevel quantum interactions modeling perspective. arXiv e-prints arXiv:1906.11081, June 2019
Shervashidze, N., Schweitzer, P., van Leeuwen, E.J., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-Lehman graph kernels. J. Machine Learn. Res. 12(77), 2539–2561 (2011). http://jmlr.org/papers/v12/shervashidze11a.html
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.i., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. arXiv e-prints arXiv:1806.03536, June 2018
Maas, A.L.: Rectifier nonlinearities improve neural network acoustic models (2013)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv e-prints arXiv:1502.03167, February 2015
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv e-prints arXiv:1412.6980, December 2014
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv e-prints arXiv:1511.07289, November 2015
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Liao, R., Zhao, Z., Urtasun, R., Zemel, R.: LanczosNet: multi-scale deep graph convolutional networks. In: ICLR (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Z., Chen, J., Chen, H. (2021). EGAT: Edge-Featured Graph Attention Network. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12891. Springer, Cham. https://doi.org/10.1007/978-3-030-86362-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-86362-3_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86361-6
Online ISBN: 978-3-030-86362-3
eBook Packages: Computer ScienceComputer Science (R0)