Deep Graph Convolutional Network with Dual-Branch and Multi-interaction
LOU Jiaqi1, YE Hailiang1, YANG Bing1, LI Ming2, CAO Feilong1
1. Department of Applied Mathematics, College of Sciences, China Jiliang University, Hangzhou 310018; 2. Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province, Zhejiang Normal University, Jinhua 321004
Abstract：Graph neural networks show excellent performance in node classification tasks. However, how to fully obtain high-order semantic features of graph data and prevent over-smoothing is one of the key issues affecting the accuracy of node classification. Therefore, deep graph convolutional network with dual-branch and multi-interaction is constructed to enhance the ability to acquire high-order semantic features of nodes. Firstly, the graph structure is reconstructed according to the feature information of the nodes. Then, a dual-branch network architecture is established by both the original and the constructed graph structures to fully extract different high-order semantic features. A channel information interaction mechanism is designed to increase the diversity of node features by learning the information interaction of different branches. Finally, experiments on multiple benchmark datasets demonstrate that the proposed method improves the accuracies of the semi-supervised node classification tasks and alleviates the over-smoothing phenomenon effectively.
楼嘉琪, 叶海良, 杨冰, 李明, 曹飞龙. 双分支多交互的深度图卷积网络[J]. 模式识别与人工智能, 2022, 35(8): 754-763.
LOU Jiaqi, YE Hailiang, YANG Bing, LI Ming, CAO Feilong. Deep Graph Convolutional Network with Dual-Branch and Multi-interaction. Pattern Recognition and Artificial Intelligence, 2022, 35(8): 754-763.
[1] GORI M, MONFARDINI G, SCARSELLI F. A New Model for Learning in Graph Domains // Proc of the IEEE International Joint Conference on Neural Networks. Washington, USA: IEEE, 2005, II: 729-734. [2] YU J L, YIN H Z, LI J D, et al. Enhancing Social Recommendation with Adversarial Graph Convolutional Networks. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3727-3739. [3] HONG D F, GAO L R, YAO J, et al. Graph Convolutional Networks for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7): 5966-5978. [4] 冯宁,郭晟楠,宋超,等.面向交通流量预测的多组件时空图卷积网络.软件学报, 2019, 30(3): 759-769. (FENG N, GUO S N, SONG C, et al. Multi-component Spatial-Temporal Graph Convolution Networks for Traffic Flow Forecasting. Journal of Software, 2019, 30(3): 759-769.) [5] SONG X G, LI H M, GAO W W, et al. Augmented Multicenter Graph Convolutional Network for COVID-19 Diagnosis. IEEE Transactions on Industrial Informatics, 2021, 17(9): 6499-6509. [6] LECUN Y, BENGIO Y.Convolutional Networks for Images, Speech, and Time Series // ARBIB M A, ed. The Handbook of Brain Theory and Neural Networks. Cambridge, USA: MIT Press, 1998: 255-258. [7] BRUNA J, ZAREMBA W, SZLAM A, ,et al. Spectral Networks and Deep Locally Connected Networks on Graphs [C/OL]. [2022-05-10]. https://arxiv.org/pdf/1312.6203.pdf. [8] SPINELLI I, SCARDAPANE S, UNCINI A.Adaptive Propagation Graph Convolutional Network. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(10): 4755-4760. [9] WU F, ZHANG T Y, DE SOUZA JR A H, et al. Simplifying Graph Convolutional Networks // Proc of the 36th International Conference on Machine Learning. San Diego, USA: JMLR, 2019: 6861-6871. [10] LI K J, YE W J.Semi-Supervised Node Classification via Graph Learning Convolutional Neural Network. Applied Intelligence, 2022. DOI: 10.1007/s10489-022-03233-9. [11] 刘臣,李自然,周立欣.基于图卷积神经网络的网络节点补全算法.模式识别与人工智能, 2021, 34(6): 532-540. (LIU C, LI Z R, ZHOU L X.Network Node Completion Based on Graph Convolutional Network. Pattern Recognition and Artificial Intelligence, 2021, 34(6): 532-540.) [12] BAI L, CUI L X, JIAO Y H, et al. Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(2): 783-798. [13] ZEB A, SAIF S, CHEN J D, et al. Complex Graph Convolutional Network for Link Prediction in Knowledge Graphs. Expert Systems with Applications, 2022, 200. DOI: 10.1016/j.eswa.2022.116796. [14] DEFFERRARD M, BRESSON X, VANDERGHEYNST P.Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering // Proc of the 30th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2016: 3844-3852. [15] KIPF T N, WELLING M.Semi-Supervised Classification with Graph Convolutional Networks[C/OL]. [2022-05-10].https://openreview.net/pdf?id=SJU4ayYgl. [16] LI M J, GUO X J, WANG Y F, et al. G2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters // Proc of the 39th International Conference on Machine Learning. San Diego, USA: JMLR, 2022: 12782-12796. [17] HAMILTON W L, YING R, LESKOVEC J.Inductive Representation Learning on Large Graphs // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 1025-1035. [18] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[C/OL].[2022-05-10]. https://openreview.net/pdf?id=rJXMpikCZ. [19] VASWANI A, SHAZEER N, PARMAR N, et al.Attention Is All You Need // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 6000-6010. [20] ZENG H Q, ZHOU H K, SRIVASTAVA A, et al. GraphSAINT: Graph Sampling Based Inductive Learning Method[C/OL].[2022-05-10]. https://openreview.net/pdf?id=BJe8pkHFwS. [21] LI Q M, HAN Z C, WU X M.Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 3538-3545. [22] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [23] RONG Y, HUANG W B, XU T Y, et al. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification[C/OL].[2022-05-10]. https://openreview.net/pdf?id=Hkx1qkrKPr. [24] CHEN M, WEI Z W, HUANG Z F, et al. Simple and Deep Graph Convolutional Networks // Proc of the 37th International Confe-rence on Machine Learning. New York, USA: ACM, 2020: 1725-1735. [25] ZHU H, KONIUSZ P.Simple Spectral Graph Convolution[C/OL]. [2022-05-10].https://openreview.net/pdf?id=CYO5T-YjWZV. [26] CHAMBERLAIN B P, ROWBOTTOM J, GORINOVA M, et al. GRAND: Graph Neural Diffusion // Proc of the 38th International Conference on Machine Learning. San Diego, USA: JMLR, 2021: 1407-1418. [27] THORPE M, XIA T D, NGUYEN T, et al. GRAND++: Graph Neural Diffusion with a Source Term[C/OL].[2022-05-10]. https://openreview.net/pdf?id=EMxu-dzvJk. [28] JIN W, DERR T, WANG Y Q, et al. Node Similarity Preserving Graph Convolutional Networks // Proc of the 14th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2021: 148-156. [29] GASTEIGER J, BOJCHEVSKI A, GÜNNEMANN S. Predict Then Propagate: Graph Neural Networks Meet Personalized PageRank[C/OL].[2022-05-10]. https://openreview.net/pdf?id=H1gL-2A9Ym. [30] DE BOER P T, KROESE D P, MANNOR S, et al. A Tutorial on the Cross-Entropy Method. Annals of Operations Research, 2005, 134(1): 19-67. [31] PASZKE A, GROSS S, MASSA F, et al.PyTorch: An Imperative Style, High-Performance Deep Learning Library // Proc of the 33rd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2019: 8026-8037. [32] KINGMA D P, BA J L. Adam: A Method for Stochastic Optimization[C/OL]. [2022-05-10]. https://arxiv.org/pdf/1412.6980.pdf. [33] SEN P, NAMATA G, BILGIC M, et al. Collective Classification in Network Data. AI Magazine, 2008, 29(3): 93-106. [34] ZHUANG C Y, MA Q.Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification // Proc of the World Wide Web Conference. New York, USA: ACM, 2018: 499-508. [35] XU K Y L, LI C T, TIAN Y L, et al. Representation Learning on Graphs with Jumping Knowledge Networks[C/OL].[2022-05-10]. https://arxiv.org/pdf/1806.03536.pdf. [36] VAN DER MAATEN L, HINTON G. Visualizing Data Using t-SNE. Journal of Machine Learning Research, 2008, 9: 2579-2605.
2022, Vol. 35 
