Skip to main content
SpringerLink
Log in

MC-GAT: Multi-Channel Graph Attention Networks for Capturing Diverse Information in Complex Graphs

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Graph attention networks (GAT), which have strong performance in tackling various analytical tasks on network data, have attracted wide attention. However, complex real-world networks have both edge topology and node features. GAT only relies on the topology of edges to extract network information, and the association between node features is underutilized, which may seriously hinder GAT’s expressive ability on some tasks. In addition, the attention mechanism can automatically assign different weights to different pieces of information, making it easier to express information with multiple aspects. Therefore, we propose semi-supervised multi-channel attention networks (MC-GAT), which simultaneously extract node features, topological structures, and their combination information. The MC-GAT model consists of two specific attention modules, one common attention module, and the attention mechanism. To create node embeddings containing various informational aspects, we use the attention mechanism to assign weights to each. Extensive testing on benchmark datasets has shown us to be at our best. The performance of the proposed model is demonstrated by the fact that MC-GAT achieves relative maximum improvements of 4.22% for accuracy (ACC) on BlogCatalog and 5.23% for macro F1-score (F1) on UAI2010. Experimental results on relevant datasets show that the method has satisfactory performance, and multi-channel graph attention can capture richer structural and feature information within linear time complexity. This work provides a new way of thinking about graph neural networks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data Availability

The data used in this paper are from the public data set, which has been quoted in the paper. And there are no ethical issues with these data. The proposed model is available at https://github.com/LZY-user/MC-GAT.

References

  1. Liu Z, Fang Y, Liu C, et al. Relative and absolute location embedding for few-shot node classification on graph. Proceedings of the AAAI conference on artificial intelligence. 2021;35(5):4267–4275.

  2. Prakash SKA, Tucker CS. Node classification using kernel propagation in graph neural networks. Expert Syst Appl. 2021;174: 114655.

    Article  Google Scholar 

  3. Smirnov V, Warnow T. MAGUS: multiple sequence alignment using graph clustering. Bioinformatics. 2021;37(12):1666–72.

    Article  Google Scholar 

  4. Patel R, Guo Y, Alhudhaif A, et al. Graph-based link prediction between human phenotypes and genes. Math Probl Eng. 2021;2022.

  5. Fan W, Ma Y, Li Q, et al. Graph neural networks for social recommendation. The world wide web conference. 2019;417–426.

  6. Chami I, Ying Z, Ré C, et al. Hyperbolic graph convolutional neural networks. Adv Neural Inf Process Syst. 2019;32.

  7. Li Q, Han Z, Wu X M. Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the AAAI conference on artificial intelligence. 2018;32(1).

  8. Wu F, Souza A, Zhang T, et al. Simplifying graph convolutional networks. International conference on machine learning. PMLR. 2019;6861–6871.

  9. Wang X, Zhu M, Bo D, et al. Am-gcn: adaptive multi-channel graph convolutional networks. Proceedings of the 26th ACM SIGKDD International conference on knowledge discovery & data mining. 2020;1243–1253.

  10. Veličković P, Cucurull G, Casanova A, et al. Graph attention networks. arXiv preprint arXiv: 1710.10903. 2017.

  11. Bruna J, Zaremba W, Szlam A, et al. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203. 2013.

  12. Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. Adv Neural Inf Process Syst. 2016;29.

  13. Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. 2016.

  14. Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs. Adv Neural Inf Process Syst. 2017;30.

  15. Wu J, He J, Xu J. Net: degree-specific graph neural networks for node and graph classification. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019;406–415.

  16. Abu-El-Haija S, Perozzi B, Kapoor A, et al. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. International conference on machine learning. PMLR. 2019;21–29.

  17. Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014;701–710.

  18. Grover A, Leskovec J. node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 2016;855–864.

  19. Perozzi B, Kulkarni V, Skiena S. Walklets: Multiscale graph embeddings for interpretable network classification. arXiv preprint arXiv:1605.02115. 2016;043238–23.

  20. Tang J, Qu M, Wang M, et al. Line: Large-scale information network embedding. Proceedings of the 24th international conference on world wide web. 2015;1067–1077.

  21. Song L, Smola A, Gretton A, et al. Supervised feature selection via dependence estimation. Proceedings of the 24th international conference on Machine learning. 2007;823–830.

  22. Wang X, Ji H, Shi C, et al. Heterogeneous graph attention network. The world wide web conference. 2019;2022–2032.

  23. Wang W, Liu X, Jiao P, et al. A unified weakly supervised framework for community detection and semantic matching. Advances in Knowledge Discovery and Data Mining: 22nd Pacific-Asia Conference, PAKDD 2018, Melbourne, VIC, Australia, June 3-6, 2018, Proceedings, Part III 22. Springer International Publishing, 2018;218-230.

  24. Meng Z, Liang S, Bao H, et al. Co-embedding attributed networks. Proceedings of the twelfth ACM international conference on web search and data mining. 2019;393–401.

  25. Van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9(11).

Download references

Funding

This work was supported in part by the following: the National Science Foundation of China (no. 62266043), the National Science and Technology Major Project (no. 95-Y50G34-9001–22/23), the Natural Science Foundation of the Autonomous Region Project (no. 2021D01C083), the Autonomous Region Science and Technology Program Youth Science Fund Project (no. 2022D01C83), and the Autonomous Region Science and Technology Department International Cooperation Project (no. 2020E01023).

Author information

Authors and Affiliations

  1. Software College, Xinjiang University, Urumqi, 830000, China

    Zhiyao La, Yurong Qian, Hongyong Leng, Tianyu Gu & Jiaying Chen

  2. Key Laboratory of signal detection and processing in Xinjiang Uygur Autonomous Region, Key Laboratory of Software Engineering, Xinjiang University, Xinjiang, China

    Zhiyao La, Yurong Qian, Tianyu Gu, Weijun Gong & Jiaying Chen

  3. School of Information Science and Engineering, Xinjiang University, Urumqi, 830000, China

    Weijun Gong

  4. School of Computer Science, Beijing Institute of Technology, Beijing, 100081, China

    Hongyong Leng

Authors
  1. Zhiyao La
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yurong Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hongyong Leng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tianyu Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Weijun Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jiaying Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

ZL: methodology and writing—original draft. YQ: writing—review and editing. HL: writing—review and editing. TG: conceptualization. WG: supervision. JC: supervision.

Corresponding author

Correspondence to Yurong Qian.

Ethics declarations

Ethical Approval

This article contains no studies with human participants or animals performed by authors.

Conflict of Interest

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

La, Z., Qian, Y., Leng, H. et al. MC-GAT: Multi-Channel Graph Attention Networks for Capturing Diverse Information in Complex Graphs. Cogn Comput 16, 595–607 (2024). https://doi.org/10.1007/s12559-023-10222-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-023-10222-8

Keywords

Search

Navigation