Abstract
Graph Neural Networks (GNNs) have made remarkable achievements on various graph tasks such as node classification, link prediction, and graph clustering. However, most GNNs focus on undirected graphs and limited effort has been made to handle directed graphs (digraphs) due to their uniqueness and complexity.
In this article, we focus on directed graphs and propose DNFS, a Digraph Neural network model with the First-order and the Second-order similarities, which can preserve unique directional information and explore complex higher-order information in the digraphs. DNFS differentiates the in-degree and out-degree similarity matrices to carefully represent directional information of the digraphs, and it considers both the first-order and the second-order similarities to capture subtle structural information. Extensive experiments on public benchmark datasets demonstrate the effectiveness of our model compared to state-of-the-art baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abu-El-Haija, S., Kapoor, A., Perozzi, B., Lee, J.: N-GCN: multi-scale graph convolution for semi-supervised node classification. In: Proceedings of the 35th Uncertainty in Artificial Intelligence Conference. Proceedings of Machine Learning Research, vol. 115, pp. 841–851. PMLR (2020)
Bojchevski, A., Günnemann, S.: Deep gaussian embedding of graphs: unsupervised inductive learning via ranking. In: International Conference on Learning Representations (2018)
Fu, B., Fu, S., Wang, L., Dong, Y., Ren, Y.: Deep residual split directed graph convolutional neural networks for action recognition. IEEE Multimedia 27(4), 9–17 (2020)
Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, pp. 639–648. Association for Computing Machinery (2020)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2017)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: graph neural networks meet personalized pagerank. In: International Conference on Learning Representations (2018)
Lieb, E.H., Loss, M.: Fluxes, Laplacians, and Kasteleyn’s Theorem, pp. 457–483. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-662-10018-9_28
Ma, Y., Hao, J., Yang, Y., Li, H., Jin, J., Chen, G.: Spectral-based graph convolutional network for directed graphs (2019)
Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. In: The Web Conference (1999)
Poignard, C., Pereira, T., Pade, J.P.: Spectra of Laplacian matrices of weighted graphs: structural genericity properties. SIAM J. Appl. Math. 78(1), 372–394 (2018)
Radmanesh, M., Ghorbanzadeh, H., Rezaei, A.A., Jalili, M., Yu, X.: Learning asymmetric embedding for attributed networks via convolutional neural network. Expert Syst. Appl. 219(C), 119659 (2023)
Sen, P., Namata, G., Bilgic, M., Getoor, L., Gallagher, B., Eliassi-Rad, T.: Collective classification in network data. In: The AI Magazine (2008)
Shchur, O., Mumme, M., Bojchevski, A., Günnemann, S.: Pitfalls of graph neural network evaluation. CoRR abs/1811.05868 (2018)
Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with directed graph neural networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7904–7913 (2019)
Tan, Z., Liu, B., Yin, G.: Asymmetric graph representation learning (2021)
Tong, Z., Liang, Y., Ding, H., Dai, Y., Li, X., Wang, C.: Directed graph contrastive learning. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19580–19593. Curran Associates, Inc. (2021)
Tong, Z., Liang, Y., Sun, C., Li, X., Rosenblum, D.S., Lim, A.: Digraph inception convolutional networks. In: Neural Information Processing Systems (2020)
Tong, Z., Liang, Y., Sun, C., Rosenblum, D.S., Lim, A.: Directed graph convolutional network. ArXiv: abs/2004.13970 (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)
Wu, F., Zhang, T., de Souza, A.H., Fifty, C., Yu, T., Weinberger, K.Q.: Simplifying graph convolutional networks. In: International Conference on Machine Learning (2019)
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 5171–5181 (2018)
Zhang, X., Liu, H., Li, Q., Wu, X.M.: Attributed graph clustering via adaptive graph convolution. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 4327–4333. AAAI Press (2019)
Zhang, X., He, Y., Brugnone, N., Perlmutter, M., Hirn, M.: Magnet: a neural network for directed graphs. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021)
Zhao, M., Jia, A.L.: A dual-attention heterogeneous graph neural network for expert recommendation in online agricultural question and answering communities. In: 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 926–931 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Y., Jia, A.L. (2023). DNFS: A Digraph Neural Network with the First-Order and the Second-Order Similarity. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14257. Springer, Cham. https://doi.org/10.1007/978-3-031-44216-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-44216-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44215-5
Online ISBN: 978-3-031-44216-2
eBook Packages: Computer ScienceComputer Science (R0)