Skip to main content
SpringerLink
Log in

Graph convolutional network with multi-similarity attribute matrices fusion for node classification

  • S.I. : Deep Social Computing
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Graph convolution networks (GCNs) have become one of the most popular deep neural network-based models in many real-world applications. GCNs can extract features take advantage of both graph structure and node attributes based on convolutional neural networks. Existing GCN models represent nodes by aggregating the graph structure and node attributes from their neighbors which usually disrupt the node similarities in the feature space. In this paper, we propose the MSF-GCN, a graph convolutional network with multi-similarity attributed matrices fusion for node classification. The key idea behind the MSF-GCN is that not only the topology but also the attributes similarities are taken into consideration for node presentation. Specifically, we first apply a GAT-based module to obtain a general representation of the original graph. Next, we construct two k-nearest neighbor graphs based on node attributes with cosine similarity and heat kernel similarity. To balance the disparity between the graph structure and node attributes for each similarity matrix, we develop a self-attention network to integrate the node attributes with topological features. Furthermore, we design a gated-fusion network to merge the cosine similarity vector and heat kernel vector. In our experiments on four real-world datasets, results show that our MSF-GCN model can extract more correlation information from the node attributes and graph structure, and outperform seven state-of-the-art methods.

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

Similar content being viewed by others

References

  1. Sun K, Zhu Z, Lin Z (2020) Multi-stage self-supervised learning for graph convolutional networks. In: Proceedings of 34th AAAI conference on artificial intelligence (AAAI 2020), AAAI, pp 5892–5899

  2. Zhao J, Zhou Z, Guan Z, et al (2019) Intentgc: a scalable graph convolution framework fusing heterogeneous information for recommendation. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD 2019), ACM, pp 2347–2357

  3. Huang Q, Wei J, Cai Y et al (2020) Aligned dual channel graph convolutional network for visual question answering. In: Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020), ACL, pp 7166–7176

  4. Qiao L, Zhao H, Huang X et al (2019) A structure-enriched neural network for network embedding. Exp Syst Appl 117:300–311

    Article  Google Scholar 

  5. Gao H, Wang Z, Ji S (2018) Large-scale learnable graph convolutional networks. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD 2018), ACM, pp 1416–1424

  6. Liu F, Xue S, Wu J et al (2020) Deep learning for community detection: progress, challenges and opportunities. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence (IJCAI-20), pp 4981–4987

  7. Su X, Xue S, Liu F et al (2021) A comprehensive survey on community detection with deep learning. arXiv preprint arXiv:2105.12584

  8. Chami I, Ying Z, Re C et al (2019) Hyperbolic graph convolutional neural networks. In: Proceedings of advances in neural information processing systems 2019 (NeurIPS 2019), pp 4868–4879

  9. Ma X, Wu J, Xue S et al (2021) A comprehensive survey on graph anomaly detection with deep learning. arXiv preprint arXiv:2106.07178

  10. Cai H, Zheng VW, Chang KC (2018) A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans Knowl Data Eng 30(9):1616–1637

    Article  Google Scholar 

  11. Zhang D, Yin J, Zhu X, Zhang C (2020) Network representation learning: a survey. IEEE Trans Big Data 6(1):3–28

    Article  Google Scholar 

  12. Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering.In: Proceedings of Advances in neural information processing systems (NeurIPS 2016), pp 3844–3852

  13. Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of advances in neural information processing systems (NeurIPS 2017), pp 1024–1034

  14. Wu L, Li Z, Zhao H, et al (2021) Learning the Implicit Semantic Representation on Graph-Structured Data. arXiv preprint arXiv:2101.06471

  15. Niepert M, Ahmed M, Kutzkov K (2016) Learning convolutional neural networks for graphs. In: Proceedings of international conference on machine learning (ICML 2016),JMLR, pp 2014–2023

  16. Jin W, Derr T, Wang Y et al (2020) Node similarity preserving graph convolutional networks. arXiv preprint arXiv:2011.09643

  17. Li Q, Han Z, Wu XM (2018) Deeper insights into graph convolutional networks for semi-supervised learning. arXiv preprint arXiv:1801.07606

  18. Franceschi L, Niepert M, Pontil M (2019) Learning discrete structures for graph neural networks. In: Proceeding of the 36th international conference on machine learning (ICML 2019), pp 1972–1982

  19. Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Aggarwal CC (ed) Social network data analytics. Springer, Boston, pp 115–148

    Chapter  Google Scholar 

  20. Tang J, Aggarwal C, Liu H (2016) Node classification in signed social networks. In: Proceedings of the 2016 SIAM international conference on data mining (SDM 2016), SIAM, pp 54–62

  21. Neville J, Jensen D (2000) Iterative classification in relational data. In: Proceedings of AAAI 2000 workshop on learning statistical models from relational data, pp 13–20

  22. Zhu X, Ghahramani Z, Lafferty JD (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of the 20th international conference on machine learning (ICML 2003), pp 912–919

  23. Zhou D, Bousquet O, Lal T, et al (2004) Learning with local and global consistency. In: Proceedings of advances in neural information processing systems (NeurIPS 2003), pp 321–328

  24. Wu J, Hong Z, Pan S et al (2014) Multi-graph-view learning for graph classification. In: 2014 IEEE international conference on data mining (ICDM 2014), IEEE, pp 590–599

  25. Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (SIGKDD 2014), ACM, pp 701–710

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

  27. Chang S, Han W, Tang J, Aggarwal CC, Huang TS et al (2015) Heterogeneous network embedding via deep architectures. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD 2015), pp 119–128

  28. Dai H, Dai B, Song L (2016) Discriminative embeddings of latent variable models for structured data. In: Proceedings of international conference on machine learning (ICML 2016), JMLR, pp 2702–2711

  29. Ou M, Cui P, Pei J, Zhang Z et al (2016) Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining (SIGKDD 2016), ACM, pp 1105–1114

  30. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceeding of 5th International conference on learning representations (ICLR 2017), pp 1–13

  31. Veli\(\check{c}\)ković P, Cucurull G, Casanova A et al (2018) Graph attention networks. In: Proceeding of 6th international conference on learning representations (ICLR 2018), pp 1–12 (2018)

  32. Jiang B, Zhang Z, Lin D et al (2019) Semi-supervised learning with graph learning-convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR 2019, pp 11313–11320

  33. Zhuang C, Ma Q (2018) Dual graph convolutional networks for graph-based semi-supervised classification. In: Proceedings of the 2018 world wide web conference (WWW 2018), ACM, pp 499–508

  34. Xu K, Li C, Tian Y et al (2018) Representation learning on graphs with jumping knowledge networks. In: Proceedings of international conference on machine learning (ICML 2018), JMLR, pp 5453–5462

  35. Wang X, Ji H, Shi C et al (2019) Heterogeneous graph attention network. In: Proceedings of The 2019 world wide web conference (WWW 2019), pp 2022–2032

  36. Xiao B, Hancock ER, Wilson RC (2009) Graph characteristics from the heat kernel trace. Pattern Recogn 42(11):2589–606

    Article  MATH  Google Scholar 

  37. Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Proceeding of Advances in neural information processing systems (NeurIPS 2017), pp 5998–6008

  38. Sen P, Namata G, Bilgic M et al (2008) Collective classification in network data. AI Mag 29(3):93–106

    Google Scholar 

  39. Zhu X, Ghahramani Z, Lafferty J (2003) Semi-supervised learning using gaussian fields and harmonic functions. In Proceedings of the 20th international conference on machine learning (ICML 2003), pp 912–919

  40. Weston J, Ratle F, Mobahi H et al (2012) Deep learning via semi-supervised embedding. Neural networks, tricks of the trade. Springer, Berlin Heidelberg, pp 639–655

    Chapter  Google Scholar 

  41. Hu F, Zhu Y, Wu S et al (2018) Hierarchical graph convolutional networks for semi-supervised node classification. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence (IJCAI 2019), pp 4532–4539

  42. Paszke A, Gross S, Massa F et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Proceedings of advances in neural information processing systems (NeurIPS 2019), pp 8026–8037

  43. Fey M, Lenssen JE (2019) Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428

  44. Tajbakhsh N, Shin J, Gurudu S et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (NSFC) under Grant Nos. 72172057, 92046026, 71701089, in part by the Fundamental Research on Advanced Leading Technology Project of Jiangsu Province under Grant BK20192004C, BK20202011, the Jiangsu Provincial Key Research and Development Program under grant BE2020001-3, the International Innovation Cooperation Project of Jiangsu Province under Grant BZ2020008, and the National Center for International Joint Research on E-Business Information Processing under Grant 2013B01035.

Author information

Authors and Affiliations

  1. Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, China

    Youquan Wang, Jie Cao & Haicheng Tao

Authors
  1. Youquan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haicheng Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jie Cao.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Cao, J. & Tao, H. Graph convolutional network with multi-similarity attribute matrices fusion for node classification. Neural Comput & Applic 35, 13135–13145 (2023). https://doi.org/10.1007/s00521-021-06429-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06429-1

Keywords

Search

Navigation