Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Erschienen in: Cognitive Computation 6/2020

06.11.2020

Graph Convolutional Network Based on Manifold Similarity Learning

verfasst von: Si-Bao Chen, Xiu-Zhi Tian, Chris H. Q. Ding, Bin Luo, Yi Liu, Hao Huang, Qiang Li

Erschienen in: Cognitive Computation | Ausgabe 6/2020

Einloggen, um Zugang zu erhalten
share
TEILEN

Abstract

In the area of large-scale graph data representation and semi-supervised learning, deep graph-based convolutional neural networks have been widely applied. However, typical graph convolutional network (GCN) aggregates information of neighbor nodes based on binary neighborhood similarity (adjacency matrix). It treats all neighbor nodes of one node equally, which does not suppress the influence of dissimilar neighbor nodes. In this paper, we investigate GCN based on similarity matrix instead of adjacency matrix of graph nodes. Gaussian heat kernel similarity in Euclidean space is first adopted, which is named EGCN. Then biologically inspired manifold similarity is trained in reproducing kernel Hilbert space (RKHS), based on which a manifold GCN (named MGCN) is proposed for graph data representation and semi-supervised learning with four different kernel types. The proposed method is evaluated with extensive experiments on four benchmark document citation network datasets. The objective function of manifold similarity learning converges very quickly on different datasets using various kernel functions. Compared with state-of-the-art methods, our method is very competitive in terms of graph node recognition accuracy. In particular, the recognition rates of MGCN (Gaussian kernel) and MGCN (Polynomial Kernel) outperform that of typical GCN about 3.8% on Cora dataset, 3.5% on Citeseer dataset, 1.3% on Pubmed dataset and 4% on Cora_ML dataset, respectively. Although the proposed MGCN is relatively simple and easy to implement, it can discover local manifold structure by manifold similarity learning and suppress the influence of dissimilar neighbor nodes, which shows the effectiveness of the proposed MGCN.

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 15 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 15 Tage kostenlos.

Literatur
1.
Zurück zum Zitat Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. 2013. arXiv preprint arXiv:​13126203 Bruna J, Zaremba W, Szlam A, LeCun Y. Spectral networks and locally connected networks on graphs. 2013. arXiv preprint arXiv:​13126203
2.
Zurück zum Zitat Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. The graph neural network model. IEEE Transactions on Neural Networks. 2008;20(1):61–80. CrossRef Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G. The graph neural network model. IEEE Transactions on Neural Networks. 2008;20(1):61–80. CrossRef
3.
Zurück zum Zitat Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in neural information processing systems. 2016;3844-3852. Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in neural information processing systems. 2016;3844-3852.
4.
5.
Zurück zum Zitat Al-Saffar AAM, Tao H, Talab MA. Review of deep convolution neural network in image classification. In: International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications. 2017;26-31. Al-Saffar AAM, Tao H, Talab MA. Review of deep convolution neural network in image classification. In: International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications. 2017;26-31.
6.
Zurück zum Zitat Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. 2017. arXiv preprint arXiv:​171010903 Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. 2017. arXiv preprint arXiv:​171010903
7.
Zurück zum Zitat Thekumparampil KK, Wang C, Oh S, Li LJ. Attention-based graph neural network for semi-supervised learning. 2018. arXiv preprint arXiv:​180303735 Thekumparampil KK, Wang C, Oh S, Li LJ. Attention-based graph neural network for semi-supervised learning. 2018. arXiv preprint arXiv:​180303735
8.
Zurück zum Zitat Wu F, Zhang T, Souza Jr AHd, Fifty C, Yu T, Weinberger KQ. Simplifying graph convolutional networks. In: International conference on machine learning. 2019;6861-6871. Wu F, Zhang T, Souza Jr AHd, Fifty C, Yu T, Weinberger KQ. Simplifying graph convolutional networks. In: International conference on machine learning. 2019;6861-6871.
9.
Zurück zum Zitat Vashishth S, Yadav P, Bhandari M, Talukdar P. Confidence-based graph convolutional networks for semi-supervised learning. 2019. arXiv preprint arXiv:​190108255 Vashishth S, Yadav P, Bhandari M, Talukdar P. Confidence-based graph convolutional networks for semi-supervised learning. 2019. arXiv preprint arXiv:​190108255
10.
Zurück zum Zitat Yang Y, Hu Y, Wu F. Sparse and low-rank subspace data clustering with manifold regulariza- tion learned by local linear embedding. Applied Sciences. 2018;8(11):2175. CrossRef Yang Y, Hu Y, Wu F. Sparse and low-rank subspace data clustering with manifold regulariza- tion learned by local linear embedding. Applied Sciences. 2018;8(11):2175. CrossRef
11.
Zurück zum Zitat Gretton A. Introduction to RKHS, and some simple kernel algorithms. Adv Top Mach Learn Lecture Conducted from University College London 16. 2013. Gretton A. Introduction to RKHS, and some simple kernel algorithms. Adv Top Mach Learn Lecture Conducted from University College London 16. 2013.
12.
Zurück zum Zitat Chen SB, Ding CH, Luo B. Similarity learning of manifold data. IEEE Transactions on Cybernetics. 2015;45(9):1744–56. CrossRef Chen SB, Ding CH, Luo B. Similarity learning of manifold data. IEEE Transactions on Cybernetics. 2015;45(9):1744–56. CrossRef
13.
Zurück zum Zitat Fangyuan L, Kewen X, Wenjia N. Improved reconstruction weight-based locally linear embedding algorithm. Journal of Image and Graphics. 2018;01. Fangyuan L, Kewen X, Wenjia N. Improved reconstruction weight-based locally linear embedding algorithm. Journal of Image and Graphics. 2018;01.
14.
Zurück zum Zitat Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. science. 2000;290(5500):2323-2326. Roweis ST, Saul LK. Nonlinear dimensionality reduction by locally linear embedding. science. 2000;290(5500):2323-2326.
15.
16.
Zurück zum Zitat Sen P, Namata G, Bilgic M, Getoor L, Galligher B, Eliassi-Rad T. Collective classification in network data. AI magazine. 2008;29(3):93–106. CrossRef Sen P, Namata G, Bilgic M, Getoor L, Galligher B, Eliassi-Rad T. Collective classification in network data. AI magazine. 2008;29(3):93–106. CrossRef
17.
Zurück zum Zitat Bojchevski A, Gunnemann S. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. 2017. arXiv preprint arXiv:​170703815 Bojchevski A, Gunnemann S. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. 2017. arXiv preprint arXiv:​170703815
18.
Zurück zum Zitat Yang Z, Cohen WW, Salakhutdinov R. Revisiting semi-supervised learning with graph embeddings. In: International conference on machine learning. 2016;40-48. Yang Z, Cohen WW, Salakhutdinov R. Revisiting semi-supervised learning with graph embeddings. In: International conference on machine learning. 2016;40-48.
20.
Zurück zum Zitat Zhu X, Ghahramani Z, Lafferty JD. Semisupervised learning using gaussian fields and harmonic functions. In: International conference on machine learning. 2003;912-919. Zhu X, Ghahramani Z, Lafferty JD. Semisupervised learning using gaussian fields and harmonic functions. In: International conference on machine learning. 2003;912-919.
21.
Zurück zum Zitat Belkin M, Niyogi P, Sindhwani V. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of machine learning research. 2006;2399-2434. Belkin M, Niyogi P, Sindhwani V. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of machine learning research. 2006;2399-2434.
22.
Zurück zum Zitat Weston J, Ratle F, Mobahi H, Collobert R. Deep learning via semi-supervised embedding. In: Neural Networks: Tricks of the Trade, Springer. 2012;639-655. Weston J, Ratle F, Mobahi H, Collobert R. Deep learning via semi-supervised embedding. In: Neural Networks: Tricks of the Trade, Springer. 2012;639-655.
23.
Zurück zum Zitat Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014. 701-710. Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014. 701-710.
24.
Zurück zum Zitat Arora S, Hu W, Kothari PK. An analysis of the t-SNE algorithm for data visualization. Conference On Learning Theory. 2018;75:1455–62. Arora S, Hu W, Kothari PK. An analysis of the t-SNE algorithm for data visualization. Conference On Learning Theory. 2018;75:1455–62.
Metadaten
Titel
Graph Convolutional Network Based on Manifold Similarity Learning
verfasst von
Si-Bao Chen
Xiu-Zhi Tian
Chris H. Q. Ding
Bin Luo
Yi Liu
Hao Huang
Qiang Li
Publikationsdatum
06.11.2020
Verlag
Springer US
Erschienen in
Cognitive Computation / Ausgabe 6/2020
Print ISSN: 1866-9956
Elektronische ISSN: 1866-9964
DOI
https://doi.org/10.1007/s12559-020-09788-4

Weitere Artikel der Ausgabe 6/2020

Cognitive Computation 6/2020 Zur Ausgabe

Premium Partner