边分类是图挖掘和社交网络分析中的一个重要研究方向。然而,现有边分类方法往往通过聚合连边端点的表示来间接提取边的特征,且设计为非端到端的学习方式,会造成较大的信息损失。针对上述问题,该文提出一种融合全局和局部信息的边分类模型EGLec(end-to-end Model with global and local Information Fusion for edge classification),将边特征提取和边分类过程建模成端到端的训练方式。首先,根据网络中所有节点对边的权重构建边的全局信息。其次,结合图自编码器和深度自编码器,分别提取网络的结构特征和边全局信息的深层语义特征,以生成连边的结构嵌入和全局特征嵌入。最后,融合结构嵌入和全局特征嵌入得到最终的连边表示以用于边分类。在三个真实数据集上的对比实验验证了该文所提出模型可显著提高边分类性能。
Abstract
Edge classification is an important research topic in the field of graph mining and social network analysis. In contrast to the non-end-to-end existing methods aggregated from nodes, we propose EGLec, i.e. an End-to-end model with Global and Local information fusion for Edge Classification, to combine the edge feature extraction and the edge classification. Specifically, we quantify global information of edges according to contribution of all nodes in the network to edges. Combined with graph auto-encoder and deep auto-encoder, we extract structure information of network and capture high-level feature of global information to generate the structure and the global feature embeddings for edges, respectively. After that, the structure embedding and global feature embedding are merged to obtain final edge representation for edge classification. Experiments on three real-world social networks demonstrate the effectiveness compared with baselines.
关键词
边分类 /
网络表示学习 /
自编码器
{{custom_keyword}} /
Key words
edge classification /
network representation learning /
auto-encoder
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] NEWMAN M E J. Networks: An introduction[M]. New York: Oxford University Press, 2010: 1-14.
[2] WANG D, CUI P, ZHU W. Structural deep network embedding[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, NY: ACM, 2016: 1225-1234.
[3] LIU Z, CHEN C, YANG X, et al. Heterogeneous graph neural networks for malicious account detection[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.New York, NY: ACM, 2018: 2077-2085.
[4] VELIˇCKOVI P, CUCURULL＇CG, CASANOVA A, et al. Graph attention networks[C]//Proceedings of the 6th International Conference on Learning Representations, 2018.
[5] WANG Z, YE X, WANG C, et al.Network embedding with completely-imbalanced labels[C]//Proceedings of the IEEE Transactions on Knowledge and Data Engineering, 2020.
[6] TANG J, AGGARWAL C, LIU H. Recommendations in signed social networks[C]//Proceedings of the 25th International Conference on World Wide Web.New York, NY: ACM, 2016: 31-40.
[7] AGGARWAL C, HE G, ZHAO P. Edge classification in networks[C]//Proceedings of the IEEE 32nd International Conference on Data Engineering.Los Alamitos, CA: IEEE Computer Society, 2016: 1038-1049.
[8] SONG C, LIN Q, LING G, et al. LoCEC: Local community-based edge classification in large online social networks[C]//Proceedings of the IEEE 36th International Conference on Data Engineering. Piscataway, NJ: IEEE, 2020: 1689-1700.
[9] 涂存超,杨成,刘知远,等. 网络表示学习综述[J]. 中国科学(信息科学), 2017, 047(008): 980-996.
[10] TANG J, QU M, WANG M, et al. LINE: Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web. New York, NY: ACM, 2015: 1067-1077.
[11] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY: ACM, 2014: 701-710.
[12] DERR T, MA Y, TANG J.Signed graph convolutional networks[C]//Proceedings of the IEEE International Conference on Data Mining. Los Alamitos, CA: IEEE Computer Society, 2018: 929-934.
[13] HUANG J, SHEN H, HOU L, et al.Signed graph attention networks[C]//Proceedings of the International Conference on Artificial Neural Networks. Berlin, German: Springer, 2019: 566-577.
[14] WANG C, WANG C, WANG Z, et al. Edge2vec: Edge-based social network embedding[J]. ACM Transactions on Knowledge Discovery from Data, 2020, 14(4): 1-24.
[15] ZHANG Z, CUI P, ZHU W. Deep learning on graphs: A survey[C]//Proceedings of the IEEE Transactions on Knowledge and Data Engineering, 2020.
[16] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations, 2017.
[17] KIPF T N, WELLING M. Variational graph auto-encoders [C]//Proceedings of the NIPS Workshop on Bayesian Deep Learning, 2016.
[18] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[C]//Proceedings of the 1st International Conference on Learning Representations, 2013.
[19] 刘忠雨,李彦霖,周洋. 深入浅出图神经网络: GNN原理解析[M]. 北京: 机械工业出版社, 2020: 197-210.
[20] 邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社,2020: 228-231.
[21] AGGARWAL C C, LI Y, YU P S, et al. On edge classification in networks with structure and content[C]//Proceedings of the IEEE 33rd International Conference on Data Engineering. Los Alamitos, CA: IEEE Computer Society, 2017: 187-190.
[22] WHITNEY H. Congruent graphs and the connectivity of graphs[M]. Boston:Birkhuser, 1992: 61-79.
[23] ZHU H, FENG F, HE X, et al. Bilinear graph neural network with neighbor interactions[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence. San Francisco, CA: Morgan Kaufmann, 2020: 1452-1458.
[24] TANG J, LOU T, KLEINBERG J. Inferring social ties across heterogeneous networks[C]//Proceedings of the 5th ACM International Conference on Web Search and Data Mining. New York, NY: ACM, 2012: 743-752.
[25] KINGMA D P, BA J.Adam: A method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representations, 2015.
[26] FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8): 861-874.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研发计划(2019YFB1704101);国家自然科学基金 (61872002);安徽省自然科学基金(2208085QF197);安徽省高校自然科学研究重点项目(2022AH05008637)
{{custom_fund}}
PDF(3969 KB)
