Abstract
Graph Convolutional Network (GCN) is increasingly becoming popular among researchers for its capability of solving the task of classification of nodes, graphs or links. Graphs being a very useful representation for several application domains are increasingly grabbing the attention of researchers. Methods are being proposed to extract meaningful information in a form which can be used by machine learning tasks. Graph convolutional networks(GCN) fall among such methods. They propagate and transform node features information. Following the message passing strategy, a Graph neural network learns a node’s embeddings representations by aggregating representations of its neighbours and itself. In this research work we incorporate the concept of overlap to the graph data thus capturing the structural similarities in the node features. The intuition behind this proposal is that the class or label of a document represented by node \({v}_{i}\) is influenced by its own node features and the node features of its neighbourhood. It is proposed to enhance the graph representation to capture this neighbourhood. This enhanced graph is then input to the graph convolutional network model for the classification task. These measures are seen to improve the accuracy of node classification. Experiments on a number of datasets with different similarity measures demonstrate that enhancing graph representations produces better results in terms of classification accuracy.
Similar content being viewed by others
Data availability
Public datasets have been used.
Code availability
Code can be made available on request.
References
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res (JMLR) 7(Nov):2399–2434
Berger-Wolf T, Taheri A, Gimpel K (2018) Learning graph representations with recurrent neural network autoencoders. In: KDD’18.
Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848. https://doi.org/10.1109/TPAMI.2017.2699184. Epub 2017 Apr 27.
Cho K, van Merriënboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: encoder–decoder approaches. Syntax, Semantics and Structure in Statistical Translation, p 103
Clough JR, Gollings J, Loach TV, Evans TS (2015) Transitive reduction of citation networks. J Complex Netw 3(2):189–203
Cui Z, Henrickson K, Ke R (2018) Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. arXiv preprintarXiv:1802.07007
Dai H, Dai B, Song L (2016) Discriminative embeddings of latent variable models for structured data. Proceedings of the 33 rd International Conference on Machine Learning, New York, NY, USA, 2016
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: 30th Conference on Neural Information Processing Systems (NIPS 2016), Barcelona, Spain
Deng J, Dong W, Socher R, Li L-J, Li K, Fei Fei L (2009) ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Fang Y, Ronald R (2001) Lattices in citation networks: An investigation into the structure of citation graphs. Scientometrics 50(2):273–287
Gao H, Wang Z, Ji S (2018) Large-scale learnable graph convolutional networks. arXiv:1808.03965v1 [cs.LG]
Gehring J, Auli M, Grangier D, Dauphin YN (2017) A convolutional encoder model for neural machine translation. Annual Meeting of the Association for Computational Linguistics
Gong C, Tao D, Liu W, Liu L, Yang J (2017) Label propagation via teaching-to-learn and learning-to-teach. IEEE Trans Neural Netw Learn Syst 28 (2017):1452–1465
Gori M, Monfardini G, Scarselli F (2005) A new model for learning in graph domains. In: Neural Networks, 2005. IJCNN’05. Proceedings. 2005 IEEE International Joint Conference on, volume 2, pp 729–734
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. ACM, New York
Hammond DK, Vandergheynst P, Gribonval R (2011) Wavelets on graphs via spectral graph theory. Appl Comput Harmon Anal 30(2):129–150
Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in Neural Information processing Systems
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. IEEE International Conference on Computer Vision
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778
Joan B, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and locally connected networks on graphs. CoRR abs/1312.6203
Karasuyama M, Mamitsuka H (2013) Manifold-based similarity adaptation for label propagation. In: Advances in Neural Information Processing Systems
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 1097–1105
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Leo E, Ronald R (1990) Introduction to Informetrics: quantitative methods in library, documentation and information science. Elsevier Science Publishers, Amsterdam, p 228. ISBN 0-444-88493-9
Leow YY, Laurent T, Bresson X (2019) GraphTSNE: a visualization technique for graph-structured data. arXiv preprint arXiv:1904.06915
Li Q, Han Z, Wu XM (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: The 32nd AAAI Conference on Artificial Intelligence
Liao R, Zhao Z, Urtasun R, Zemel RS, Lanczosnet (2019) Multi-scale deep graph convolutional networks. In: Proceedings of the 7th International Conference on Learning Representations
Liu Y, Lee J, Park M, Kim S, Yang E, Hwang SJ, Yang Y (2019a) Learning to propagate labels: Transductive propagation network for few-shot learning. In: Proceedings of the 7th International Conference on Learning Representations
Luong M-T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. Conference on Empirical Methods in Natural Language Processing
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems (NIPS), pp 3111–3119
Monti F, Bronstein M, Bresson X (2017) Geometric matrix completion with recurrent multi-graph neural networks. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, pp 3697–3707
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. ACM, New York
Qu M, Bengio Y, Tang J, Gmnn (2019) Graph markov neural networks. In: Proceedings of the 36th International Conference on Machine Learning
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, 91–99
Seo Y, Defferrard M, Vandergheynst P (2018) Structured sequence modeling with graph convolutional recurrent networks. International Conference on Neural Information Processing, 362-373
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Networks 20(1):61–80
Sen P, Namata G, Bilgic M, Getoor L, Galligher B, Eliassi-Rad T (2008) Collective classification in network data. AI Mag 29(3):93
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations
Shi X, Lv F, Seng D, Zhang J, Chen J, Xing B (2021) Visualizing and understanding graph convolutional network. Multimed Tools Appl 80:8355–8375. https://doi.org/10.1007/s11042-020-09885-4
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Sun Y, Liang J, Niu P (2021) Personalized recommendation of english learning based on knowledge graph and graph convolutional network. In: Sun X, Zhang X, Xia Z, Bertino E (eds) Artificial Intelligence and Security. ICAIS 2021, vol 12737. Springer, Cham. https://doi.org/10.1007/978-3-030-78612-0_13
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web. ACM, New York, pp 1067–1077
Thomas K, Welling M (2017) Semi-Supervised Classification with Graph Convolutional Networks. In: Proceedings of the 5th International Conference on Learning representation
Veličković P, Cucurull G, Casanova A et al (2018) Graph attention networks. In: Proceedings of the International Conference on Learning Representations
Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, New York, pp 1225–1234
Wang F, Zhang C (2008) Label propagation through linear neighborhoods. IEEE Trans Knowl Data Eng 20(1):55–67. https://doi.org/10.1109/TKDE.2007.190672
Wang H, Leskovec J (2020) Unifying graph convolutional neural networks and label propagation. arXiv:2002.06755v1 [cs.LG]
Wangzhong L, Janssen J, Milios E, Japkowic N, Yongzheng Z (2007) Node similarity in the citation graph. Knowl Inf Syst 11(1):105–129
Weston J, Ratle F, Mobahi H, Collobert R (2012) Deep learning via semi supervised embedding. Neural Networks: Tricks of the Trade. Springer, Berlin, pp 639–655
Xiao G, Wang R, Zhang C et al (2021) Demand prediction for a public bike sharing program based on spatio-temporal graph convolutional networks. Multimed Tools Appl 80:22907–22925. https://doi.org/10.1007/s11042-020-08803-y
Xiao L, Hu X, Chen Y et al (2020) Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-10107-0
Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations
Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K-i, Jegelka S (2018) Representation learning on graphs with jumping knowledge networks. In: Proceedings of the 35th International Conference on Machine Learning
Yi L, Su H, Guo X et al (2017) Syncspeccnn: synchronized spectral cnn for 3d shape segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2282-2290
Ying R, He R, Chen K (2018) et.al., Graph convolutional networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 974-983
Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, 3634-3640
Yuan A, Jeannette J, Evangelos EM (2004) Characterizing and mining the citation graph of the computer science literature. Knowl Inf Syst 6(6):664–678
Zhang B, Liu M, Zhou B, Liu X (2021) Graph learning in low dimensional space for graph convolutional networks. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-11033-5
Zhang Z, Wang J, Mlle (2007) Modified locally linear embedding using multiple weights. In: Adv Neural Inf Process Syst 19:1593–1600
Zhao, Dangzhi Z, Andreas S (2015) Analysis and visualization of citation networks. Morgan & Claypool Publishers, San Rafael. ISBN 978-1-60845-939-1
Zhou K, Song Q, Huang X, Hu X ( 2019) Auto-GNN: Neural architecture search of graph neural networks. arXiv:1909.03184v2 [cs.LG]
Zhu X, Ghahramani Z, Lafferty J (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: International Conference on Machine Learning (ICML), vol 3, pp 912–919
Zhu X, Mao Z, Chen Z et al (2021) Object-difference drived graph convolutional networks for visual question answering. Multimed Tools Appl 80:16247–16265. https://doi.org/10.1007/s11042-020-08790-0
Zhu X, Lafferty J, Rosenfeld R (2005) Semi-supervised learning with graphs. PhD thesis, Carnegie Mellon University, school of language technologies institute
Zitnik M, Leskovec J (2017) Predicting multicellular function through multi-layer tissue networks. Bioinformatics 33(14):i190–i198
Acknowledgements
The authors gratefully acknowledge the valuable suggestions provided by the anonymous reviewers which greatly helped in preparing the paper in its present form.
Funding
The research has been supported by Birla Institute of Technology, Mesra, Ranchi.
Author information
Authors and Affiliations
Contributions
The first author is responsible for conceptualization, problem definition, solution design and report writing. The second author is responsible for implementation and support in report writing. The third author is responsible for implementation and support in report writing.
Corresponding author
Ethics declarations
Conflicts of interest/Competing interests
None.
Ethics approval
Not applicable.
Consent to participate
All the authors are aware of this submission. They have reviewed and consented to participate in this journal submission.
Consent for publication
All the authors are aware of this submission. They have reviewed and consented to participate in this journal submission.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bhattacharjee, V., Sahu, R. & Dutta, A. Enhanced Graph Representations for Graph Convolutional Network Models. Multimed Tools Appl 82, 9649–9666 (2023). https://doi.org/10.1007/s11042-021-11843-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11843-7