Abstract Most link prediction models rely too much on the known link information while mining node similarity. However, the number of the known observed links is small in the real world. To improve the robustness of the model, it is crucial to decouple the dependence of the model on the link information and mine the underlying features of nodes. In this paper, a link prediction model based on adversarial graph convolutional network is proposed with the consideration of the potential relationship between node features and links. Firstly, the similarity metric between nodes is utilized to fill in some unknown links in the adjacency matrix to alleviate the influence of link sparsity on the graph convolution model. Then, the adversarial network is employed to deeply mine the underlying connections between node features and links to reduce the dependence of the model on links. Experiments on real datasets show that the proposed model achieves better performance on link prediction problem and the performance remains relatively stable under link sparsity. Moreover, the proposed model is applicable to large-scale datasets.
Corresponding Authors:
ZHAO Jieyu, Ph.D., professor. His research interests include computational intelligence, pattern recognition and natural human-computer interaction.
About author:: YE Xulun, Ph.D., lecturer. His research interests include Bayesian learning and convex optimization. YU Shushi, master student. Her research interests include generative adversarial networks and pattern recognition.
[1] STANFIELD Z, COSKUN M, KOYUTÜRK M. Drug Response Prediction as a Link Prediction Problem. Scientific Reports, 2017, 7(1): 1-13. [2] GUO L, MA J, CHEN Z M, et al. Learning to Recommend with Social Contextual Information from Implicit Feedback. Soft Computing, 2015, 19(5): 1351-1362. [3] LI X, CHEN H. Recommendation as Link Prediction in Bipartite Graphs: A Graph Kernel-Based Machine Learning Approach. Decision Support Systems, 2013, 54(2): 880-890. [4] GENG X, LI Y G, WANG L Y, et al. Spatiotemporal Multi-graph Convolution Network for Ride-Hailing Demand Forecasting // Proc of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 3656-3663. [5] GUO S N, LIN Y F, FENG N, et al. Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting // Proc of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 922-929. [6] NEWMAN M E J. Clustering and Preferential Attachment in Growing Networks. Physical Review E, 2001, 64. DOI: 10.1103/PhysRevE.64.025102. [7] LIBEN-NOWELL D, KLEINBERG J. The link-Prediction Problem for Social Networks. Journal of the American Society for Information Science and Technology, 2007, 58(7): 1019-1031. [8] JEH G, WIDOM J. SimRank: A Measure of Structural-Context Si-milarity // Proc of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2002: 538-543. [9] AHMED N M, CHEN L, WANG Y L, et al. DeepEye: Link Prediction in Dynamic Networks Based on Non-negative Matrix Factorization. Big Data Mining and Analytics, 2018, 1(1): 19-33. [10] MENON A K, ELKAN C. Link Prediction via Matrix Factorization // Proc of the European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2011, II: 437-452. [11] GUIMERÀ R, SALES-PARDO M. Missing and Spurious Interactions and the Reconstruction of Complex Networks. Proceedings of the National Academy of Sciences of the United States of America, 2009, 106(52): 22073-22078. [12] DE SÁ H R,PRUDÊNCIO R B C.Supervised Link Prediction in Weighted Networks // Proc of the International Joint Conference on Neural Networks. Washington, USA: IEEE, 2011: 2281-2288. [13] KIPF T N, WELLING M. Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2020-08-27]. http://arxiv.org/pdf/1609.02907.pdf. [14] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling Relational Data with Graph Convolutional Networks // Proc of the European Semantic Web Conference. Berlin, Germany: Springer, 2018: 593-607. [15] YANG B S, YIH W T, HE X D, et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1412.6575.pdf. [16] SHANG C, TANG Y, HUANG J, et al. End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion // Proc of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 3060-3067. [17] LI W D, ZHANG X Y, WANG Y Q, et al. Graph2Seq: Fusion Embedding Learning for Knowledge Graph Completion. IEEE Access, 2019, 7: 157960-157971. [18] KIPF T N, WELLING M. Variational Graph Auto-encoders[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1611.07308.pdf. [19] PAN S R, HU R Q, FUNG S F, et al. Learning Graph Embedding with Adversarial Training Methods. IEEE Transactions on Cybernetics, 2020, 50(6): 2475-2487. [20] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative Adversarial Nets // Proc of the 27th International Confe-rence on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2014, II: 2672-2680. [21] GROVER A, LESKOVEC J. node2vec: Scalable Feature Learning for Networks // Proc of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2016: 855-864. [22] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral Networks and Locally Connected Networks on Graphs[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1312.6203.pdf. [23] 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: The MIT Press, 2016: 3844-3852. [24] NIEPERT M, AHMED M, KUTZKOV K. Learning Convolutional Neural Networks for Graphs // Proc of the 33rd International Conference on Machine Learning. Berlin, Germany: Springer, 2016: 2014-2023. [25] HAMILTON W L, YING Z, LESKOVEC J. Inductive Representation Learning on Large Graphs // Proc of the 31st International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2017: 1025-1035. [26] CHEN J F, MA T F, XIAO C. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1801.10247.pdf. [27] CHEN J F, ZHU J, SONG L, et al. Stochastic Training of Graph Convolutional Networks with Variance Reduction // Proc of the 35th International Conference on Machine Learning. Berlin, Germany: Springer, 2018: 942-950. [28] VELICˇKOVIC P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1710.10903.pdf. [29] MIRZA M, OSINDERO S. Conditional Generative Adversarial Nets[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1411.1784.pdf. [30] RADFORD A, METZ L, CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[C/OL]. [2020-08-27]. https://arxiv.org/pdf/1511.06434.pdf. [31] ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein Generative Adversarial Networks // Proc of the 34th International Conference on Machine Learning. Berlin, Germany: Springer, 2017: 214-223. [32] BEN-DAVID S, BLITZER J, CRAMMER K, et al. A Theory of Learning from Different Domains. Machine Learning, 2010, 79(1/2): 151-175. [33] SEN P, NAMATA G, BILGIC M, et al. Collective Classification in Network Data. AI Magazine, 2008, 29(3): 93-106. [34] PEROZZI B, AL-RFOU R, SKIENA S. Deepwalk: Online Lear-ning of Social Representations // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014: 701-710. [35] TANG L, LIU H. Leveraging Social Media Networks for Classification. Data Mining and Knowledge Discovery, 2011, 23(3): 447-478. [36] STARK C, BREITKREUTZ B J, REGULY T, et al. BioGRID: A General Repository for Interaction Datasets. Nucleic Acids Research, 2006, 34: D535-D539. [37] TANG J, QU M, WANG M Z, et al. Line: Large-Scale Information Network Embedding // Proc of the 24th International Confe-rence on World Wide Web. Berlin, Germany: Springer, 2015: 1067-1077. [38] ZHANG M H, CHEN Y X. Weisfeiler-Lehman Neural Machine for Link Prediction // Proc of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2017: 575-583.
2021, Vol. 34 
