E-GCN: graph convolution with estimated labels


G raph C onvolutional N etwork (GCN) has been commonly applied for semi-supervised learning tasks. However, the established GCN frequently only considers the given labels in the topology optimization, which may not deliver the best performance for semi-supervised learning tasks. In this paper, we propose a novel G raph C onvolutional N etwork with E stimated labels (E-GCN) for semi-supervised learning. The core design of E-GCN is to learn a suitable network topology for semi-supervised learning by linking both estimated labels and given labels in a centralized network framework. The major enhancement is that both given labels and estimated labels are utilized for the topology optimization in E-GCN, which assists the graph convolution implementation for unknown labels evaluation. Experimental results demonstrate that E-GCN is significantly better than s tate-o f-t he-a rt (SOTA) baselines without estimated labels.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4


  1. 1.

    Wei X, Xu L, Cao B, et al. (2017) Cross view link prediction by learning noise-resilient representation consensus. In: Proceedings of the 26th international conference on World Wide Web, pp 1611–1619

  2. 2.

    Gao M, Chen L, Li B, et al. (2018) A link prediction algorithm based on low-rank matrix completion. Applied Intelligence 48(12):4531–4550

    Article  Google Scholar 

  3. 3.

    Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907

  4. 4.

    Ying R, He R, Chen K, et al. (2018) Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 974–983

  5. 5.

    Zhang C, Li T, Ren Z, et al. (2019) Taxonomy-aware collaborative denoising autoencoder for personalized recommendation. Applied Intelligence 49(6):2101–2118

    Article  Google Scholar 

  6. 6.

    Fortunato S, Hric D (2016) Community detection in networks: a user guide. Physics Reports 659:1–44

    MathSciNet  Article  Google Scholar 

  7. 7.

    Tao Z, Liu H, Li S, et al. (2017) From ensemble clustering to multi-view clustering. In: IJCAI

  8. 8.

    Wang T, Liu L, Liu N, Zhang H, et al. (2020) A multi-label text classification method via dynamic semantic representation model and deep neural network. Applied Intelligence 50:2339–2351

    Article  Google Scholar 

  9. 9.

    Li M, Ma Z, Wang YG, et al. (2020) Fast Haar transforms for graph neural networks. Neural Networks

  10. 10.

    Wang YG, Li M, Ma Z, et al. (2020) Haar graph pooling. In: ICML

  11. 11.

    Yang L, Kang Z, Cao X, et al. (2019) Topology optimization based graph convolutional network. In: IJCAI, pp 4054–4061

  12. 12.

    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, pp 701–710

  13. 13.

    Abu-El-Haija S, Kapoor A, Perozzi B, et al. (2018) N-gcn: multi-scale graph convolution for semi-supervised node classification. arXiv:1802.08888

  14. 14.

    Thekumparampil KK, Wang C, Oh S, et al. (2018) Attention-based graph neural network for semi-supervised learning. arXiv:1803.03735

  15. 15.

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

  16. 16.

    Yu B, Yin H, Zhu Z (2017) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. arXiv:1709.04875

  17. 17.

    Jiang J, Cui Z, Xu C, et al. (2019) Gaussian-induced convolution for graphs. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 4007–4014

  18. 18.

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

  19. 19.

    Li Q, Han Z, Wu XM (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: Thirty-Second AAAI conference on artificial intelligence

  20. 20.

    Wang X, Qian B, Davidson I (2012) Labels vs. pairwise constraints: a unified view of label propagation and constrained spectral clustering. In: 2012 IEEE 12th international conference on data mining, pp 1146–1151

  21. 21.

    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-03), pp 912–919

  22. 22.

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

    Book  Google Scholar 

  23. 23.

    Lu Q, Getoor L (2003) Link-based classification. In: Proceedings of the 20th international conference on machine learning (ICML-03), pp 496–503

  24. 24.

    Yang Z, Cohen W (2016) Revisiting semi-supervised learning with graph embeddings. arXiv:1603.08861

  25. 25.

    Monti F, Boscaini D, Masci J, et al. (2017) Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5115–5124

  26. 26.

    Du J, Zhang S, Wu G, et al. (2017) Topology adaptive graph convolutional networks. arXiv:1710.10370

  27. 27.

    Zhuang C, Ma Q (2017) Dual graph convolutional networks for graph-based semi-supervised classification. In: Proceedings of the 2018 World Wide Web conference, pp 499–508

Download references


This work was supported by the National Natural Science Foundation of China (No. 61170089, No. 60971088).

Author information



Corresponding author

Correspondence to Xiaoqin Zeng.

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

Verify currency and authenticity via CrossMark

Cite this article

Qin, J., Zeng, X., Wu, S. et al. E-GCN: graph convolution with estimated labels. Appl Intell 51, 5007–5015 (2021). https://doi.org/10.1007/s10489-020-02093-5

Download citation


  • Semi-supervised
  • Learning graph convolution
  • Topology optimization
  • Estimated labels