Abstract
Over the past few years, graph representation learning (GRL) has received widespread attention on the feature representations of the non-Euclidean data. As a typical model of GRL, graph convolutional networks (GCN) fuse the graph Laplacian-based static sample structural information. GCN thus generalizes convolutional neural networks to acquire the sample representations with the variously high-order structures. However, most of existing GCN-based variants depend on the static data structural relationships. It will result in the extracted data features lacking of representativeness during the convolution process. To solve this problem, dynamic graph learning convolutional networks (DGLCN) on the application of semi-supervised classification are proposed. First, we introduce a definition of dynamic spectral graph convolution operation. It constantly optimizes the high-order structural relationships between data points according to the loss values of the loss function, and then fits the local geometry information of data exactly. After optimizing our proposed definition with the one-order Chebyshev polynomial, we can obtain a single-layer convolution rule of DGLCN. Due to the fusion of the optimized structural information in the learning process, multi-layer DGLCN can extract richer sample features to improve classification performance. Substantial experiments are conducted on citation network datasets to prove the effectiveness of DGLCN. Experiment results demonstrate that the proposed DGLCN obtains a superior classification performance compared to several existing semi-supervised classification models.
- Andrie Alexandrescu and Katrin Kirchhoff. 2007. Graph-based learning for phonetic classification. In Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding. 359–364.Google Scholar
Cross Ref
- Walter Allegretto and Huang Yin Xi. 1998. A Picone’s identity for the p-Laplacian and applications. Nonlin. Anal.: Theor., Meth. Applic. 32, 7 (1998), 819–830. Google Scholar
Digital Library
- James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 1993–2001. Google Scholar
Digital Library
- Jun Bai, Shiming Xiang, and Chunhong Pan. 2013. A graph-based classification method for hyperspectral images. IEEE Trans. Geosci. Rem. Sens. 51, 2 (2013), 803–817.Google Scholar
Cross Ref
- Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. 2006. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, Nov. (2006), 2399–2434. Google Scholar
Digital Library
- Cecile Cabanes, A. Grouazel, K. von Schuckmann, M. Hamon, Victor Turpin, C. Coatanoan, F. Paris, S. Guinehut, C. Boone, N. Ferry, et al. 2013. The CORA dataset: Validation and diagnostics of in-situ ocean temperature and salinity measurements. Ocean Sci. 9, 1 (2013), 1–18.Google Scholar
Cross Ref
- Yu Cao, Meng Fang, and Dacheng Tao. 2019. BAG: Bi-directional attention entity graph convolutional network for multi-hop reasoning question answering. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 357–362.Google Scholar
- Diane J. Cook and Lawrence B. Holder. 1993. Substructure discovery using minimum description length and background knowledge. J. Artif. Intell. Res. 1 (1993), 231–255. Google Scholar
Digital Library
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 3844–3852. Google Scholar
Digital Library
- Sichao Fu, Weifeng Liu, Yicong Zhou, and Liqiang Nie. 2019. HpLapGCN: Hypergraph p-Laplacian graph convolutional networks. Neurocomputing 362 (2019), 166–174.Google Scholar
Digital Library
- Yue Gao and Qionghai Dai. 2014. Efficient view-based 3-D object retrieval via hypergraph learning. Tsinghua Sci. Technol. 19, 3 (2014), 250–256.Google Scholar
- Yue Gao, Meng Wang, Dacheng Tao, Rongrong Ji, and Qionghai Dai. 2012. 3-D object retrieval and recognition with hypergraph analysis. IEEE Trans. Image Proc. 21, 9 (2012), 4290–4303. Google Scholar
Digital Library
- Bo Geng, Dacheng Tao, Chao Xu, Linjun Yang, and Xian-Sheng Hua. 2012. Ensemble manifold regularization. IEEE Trans. Pattern Anal. Mach. Intell. 34, 6 (2012), 1227–1233. Google Scholar
Digital Library
- Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 249–256.Google Scholar
- Yin Hong, Yanxia Liu, Suizhu Yang, Kaiwen Zhang, Aiqing Wen, and Jianjun Hu. 2020. Improving graph convolutional networks based on relation-aware attention for end-to-end relation extraction. IEEE Access 8 (2020), 51315–51323.Google Scholar
Cross Ref
- Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, and Patrick Riley. 2016. Molecular graph convolutions: Moving beyond fingerprints. J. Comput.-aided Molec. Des. 30, 8 (2016), 595–608.Google Scholar
- Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference of Learning Representation.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 6th International Conference of Learning Representation.Google Scholar
- Frank Lambert. 2010. Online community information seeking: The queries of three communities in Southwestern Ontario. Inf. Proc. Manag. 46, 3 (2010), 343–361. Google Scholar
Digital Library
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper insights into graph convolutional networks for semi-supervised learning. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.Google Scholar
- Weifeng Liu, Hongli Liu, Dapeng Tao, Yanjiang Wang, and Ke Lu. 2015. Multiview Hessian regularized logistic regression for action recognition. Sig. Proc. 110 (2015), 101–107. Google Scholar
Digital Library
- Weifeng Liu, Zheng-Jun Zha, Yanjiang Wang, Ke Lu, and Dacheng Tao. 2016. \(\)-Laplacian regularized sparse coding for human activity recognition. IEEE Trans. Industr. Electron. 63, 8 (2016), 5120–5129.Google Scholar
- Xiao Liu, Jun Shi, and Congzhi Wang. 2015. Hessian regularization based non-negative matrix factorization for gene expression data clustering. In Proceedings of the 37th International Conference of the IEEE Engineering in Medicine and Biology Society. 4130–4133.Google Scholar
- Yong Luo, Dacheng Tao, Bo Geng, Chao Xu, and Stephen J. Maybank. 2013. Manifold regularized multitask learning for semi-supervised multilabel image classification. IEEE Trans. Image Proc. 22, 2 (2013), 523–536. Google Scholar
Digital Library
- Xueqi Ma, Weifeng Liu, Shuying Li, Dapeng Tao, and Yicong Zhou. 2019. Hypergraph \(\)-Laplacian regularization for remotely sensed image recognition. IEEE Trans. Geosci. Rem. Sens. 57, 3 (2019), 1585–1595.Google Scholar
Cross Ref
- Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, and Jie Tang. 2018. DeepInf: Social influence prediction with deep learning. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2110–2119. Google Scholar
Digital Library
- Rafael Rodriguez-Puente and Manuel S. Lazo-Cortes. 2012. Graph-reduction algorithm for finding shortest path in geographic information systems. IEEE Lat. Amer. Trans. 10, 6 (2012), 2201–2208.Google Scholar
Cross Ref
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI Mag. 29, 3 (2008), 93–93.Google Scholar
Digital Library
- Andrea Vedaldi and Karel Lenc. 2015. MatConvNet: Convolutional neural networks for MATLAB. In Proceedings of the 23rd International Conference on Multimedia. 689–692. Google Scholar
Digital Library
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 7th International Conference of Learning Representation.Google Scholar
- Yang Wang. 2020. Survey on deep multi-modal data analytics: Collaboration, rivalry and fusion. ACM Trans. Multim. Comput. Commun. Applic. (2020). DOI:10.1145/1122445.1122456Google Scholar
Digital Library
- Yan Wang, Hao Zhang, Yaxin Li, Deyun Wang, YanLin Ma, Tong Zhou, and Jianguo Lu. 2016. A data cleaning method for Citeseer dataset. In Proceedings of the International Conference on Web Information Systems Engineering. 35–49.Google Scholar
Cross Ref
- Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, Meng Fang, and Shirui Pan. 2016. Iterative views agreement: An iterative low-rank based structured optimization method to multi-view spectral clustering. In Proceedings of the International Joint Conference on Artificial Intelligence. 2153–2159. Google Scholar
Digital Library
- Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, and Xiang Zhao. 2017. Unsupervised metric fusion over multiview data by graph random walk-based cross-view diffusion. IEEE Trans. Neural Netw. Learn. Syst. 28, 1 (2017), 57–70.Google Scholar
Cross Ref
- Jason Weston, Frédéric Ratle, Hossein Mobahi, and Ronan Collobert. 2012. Deep learning via semi-supervised embedding. In Neural Networks: Tricks of the Trade. Springer, 639–655.Google Scholar
Digital Library
- Jia Wu, Shirui Pan, Xingquan Zhu, Chengqi Zhang, and S. Yu Philip. 2018. Multiple structure-view learning for graph classification. IEEE Trans. Neural Netw. Learn. Syst. 29, 7 (2018), 3236–3251.Google Scholar
- Lin Wu, Yang Wang, Junbin Gao, and Xue Li. 2019. Where-and-when to look: Deep Siamese attention networks for video-based person re-identification. IEEE Trans. Multim. 21, 6 (2019), 1412–1424.Google Scholar
Digital Library
- Lin Wu, Yang Wang, Junbin Gao, and Dacheng Tao. 2021. Deep co-attention based comparators for relative representation learning in person re-identification. IEEE Trans. Neural Netw. Learn. Syst. 32, 2 (2021), 722--735.Google Scholar
Cross Ref
- Lin Wu, Yang Wang, and Ling Shao. 2019. Cycle-consistent deep generative hashing for cross-modal retrieval. IEEE Trans. Image Proc. 28, 4 (2019), 1602–1612.Google Scholar
Digital Library
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).Google Scholar
- Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In Proceedings of the International Conference on Machine Learning.Google Scholar
- Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Anand Louis, and Partha Talukdar. 2018. HyperGCN: Hypergraph convolutional networks for semi-supervised classification. In Proceedings of the International Conference on Multimedia and Expo.Google Scholar
- Yunyun Yang and Gang Xie. 2016. Efficient identification of node importance in social networks. Inf. Proc. Manag. 52, 5 (2016), 911–922. Google Scholar
Digital Library
- Sławomir Zadrożny, Janusz Kacprzyk, and Guy De Tré. 2012. Bipolar queries in textual information retrieval: A new perspective. Inf. Proc. Manag. 48, 3 (2012), 390–398. Google Scholar
Digital Library
- Wenjie Zhang, Lin Wu, Yang Wang, and Xuemin Lin. 2017. Effective multi-query expansions: Collaborative deep networks for robust landmark retrieval. IEEE Trans. Image Proc. 26, 3 (2017), 1393–1404. Google Scholar
Digital Library
- Lefei Zhang, Qian Zhang, Liangpei Zhang, Dacheng Tao, Xin Huang, and Bo Du. 2015. Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding. Pattern Recog. 48, 10 (2015), 3102–3112. Google Scholar
Digital Library
- Yongsheng Zhang, Tsuyoshi Yamamoto, and Yoshinori Dobashi. 2016. Multi-scale object retrieval via learning on graph from multimodal data. Neurocomputing 207 (2016), 684–692. Google Scholar
Digital Library
- Zhao Zhang, Sun Yulin, Yang Wang, Zheng Zhang, and Meng Wang. 2020. Twin-incoherent self-expressive locality-adaptive latent dictionary pair learning for classification. IEEE Trans. Neural Netw. Learn. Syst. (2020). DOI:10.1109/TNNLS.2020.2979748Google Scholar
- Nengwen Zhao, Lefei Zhang, Bo Du, Qian Zhang, Jane You, and Dacheng Tao. 2017. Robust dual clustering with adaptive manifold regularization. IEEE Trans. Knowl. Data Eng. 29, 11 (2017), 2498–2509.Google Scholar
Cross Ref
- Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2018. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434 (2018).Google Scholar
- Xiang Zhou, Fumin Shen, Li Liu, Wei Liu, Liqiang Nie, Yang Yang, and Heng Tao Shen. 2020. Graph convolutional network hashing. IEEE Trans. Syst., Man Cyber. 50, 4 (2020), 1460–1472.Google Scholar
Index Terms
Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification
Recommendations
Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification
WWW '18: Proceedings of the 2018 World Wide Web ConferenceThe problem of extracting meaningful data through graph analysis spans a range of different fields, such as the internet, social networks, biological networks, and many others. The importance of being able to effectively mine and learn from such data ...
Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints
AbstractGraph convolutional networks (GCNs), as an extension of classic convolutional neural networks (CNNs) in graph processing, have achieved good results in completing semi-supervised learning tasks. Traditional GCNs usually use fixed graph to complete ...
Graph Convolutional Networks based on manifold learning for semi-supervised image classification
AbstractDue to a huge volume of information in many domains, the need for classification methods is imperious. In spite of many advances, most of the approaches require a large amount of labeled data, which is often not available, due to costs ...
Highlights- A novel approach based on Graph Conv. Net. (GCN) for semi-supervised classification.






Comments