基于对抗图卷积的网络表征学习框架

doi:10.16451/j.cnki.issn1003-6059.201911009

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (645 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要现有的网络表征方法及其相关变体的侧重点在于保存网络的拓扑结构或使重构误差最小,忽略隐变量的数据分布问题.基于此种情况,文中提出基于对抗图卷积的网络表征学习框架(AGCN),使网络模型不仅可以组合图的结构信息和节点的属性信息,提高网络表征学习性能,而且可以学习数据分布.与此同时,在AGCN的基础上提出端到端的多任务学习框架(MTL),在一个学习阶段可以同时进行链接预测和节点分类任务.实验表明,MTL性能较优.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈梦雪
	刘勇

关键词 ：网络表征, 链接预测, 节点分类, 多任务学习

Abstract：The existing network representation methods and their related variants are focused on preserving network topology structure or minimizing reconstruction error. However, data distribution of latent codes is ignored. To solve the problem, an adversarial graph convolutional networks(AGCN) is proposed. AGCN combines graph structure information and node attribute information to improve network representation learning performance, and enforces the latent codes to match a prior distribution. Moreover, an end-to-end multi-task learning framework(MTL) based on AGCN is introduced. It can perform link prediction and node classification simultaneously. The experiment shows that MTL achieves a good performance.

Key words： Network Representation Link Prediction Node Classification Multi-task Learning

收稿日期: 2019-08-24

ZTFLH:

TP 183

基金资助:国家自然科学基金项目(No.61972135,61602159)、黑龙江省自然科学基金项目(No.F201430)、黑龙江省高校基本科研业务费项目(No.HDJCCX-201608,KJCX201815,2018-KYYWF-1565)、哈尔滨科技创新人才研究专项资金项目(No.2017RAQXJ094,2017RAQXJ131)

通讯作者: 刘勇,博士,副教授,主要研究方向为数据挖掘、数据库等.E-mail:acliuyong@sina.com.

作者简介: 陈梦雪,硕士研究生,主要研究方向为链接预测.E-mail:2370929923@qq.com.

引用本文:

陈梦雪, 刘勇. 基于对抗图卷积的网络表征学习框架[J]. 模式识别与人工智能, 2019, 32(11): 1042-1050. CHEN Mengxue, LIU Yong. Network Representation Learning Framework Based on Adversarial Graph Convolutional Networks. , 2019, 32(11): 1042-1050.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201911009 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2019/V32/I11/1042

[1] PEROZZI B, ALRFOU R, SKIENA S, et al. DeepWalk: Online Learning of Social Representations[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1403.6652.pdf.
[2] 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.
[3] 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.
[4] OU M D, CUI P, PEI J, et al. Asymmetric Transitivity Preserving Graph Embedding[C/OL]. [2019-07-20]. https://www.kdd.org/kdd2016/papers/files/rfp0184-ouA.pdf.
[5] CAO S S, LU W, XU Q K, et al. GraRep: Learning Graph Representations with Global Structural Information // Proc of the 24th ACM International Conference on Information and Knowledge Management. Berlin, Germany: Sprin-ger, 2015: 891-900.
[6] WANG D X, CUI P, ZHU W W, et al. Structural Deep Network Embedding[C/OL]. [2019-07-20]. https://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf.
[7] CAO S S, LU W, XU Q K, et al. Deep Neural Networks for Lear-ning Graph Representations // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 1145-1152.
[8] YANG C, LIU Z Y, ZHAO D L, et al. Network Representation Learning with Rich Text Information // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 2111-2117.
[9] KIPF T N, WELLING M. Semi-Supervised Classification with Graph Convolutional Networks[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1609.02907.pdf.
[10] KINGMA D P, WELLING M. Auto-Encoding Variational Bayes[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1312.6114.pdf.
[11] VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and Composing Robust Features with Denoising Autoencoders // Proc of the 25th International Conference on Machine Learning. New York, USA: ACM, 2008: 1096-1103.
[12] GOODFELLOW I J, PIUGET-ABADIE J, MIRZA M, et al. Ge-nerative Adversarial Nets[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1406.2661v1.pdf.
[13] MIRZA M, OSINDERO S. Conditional Generative Adversarial Nets[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1411.1784.pdf.
[14] RADFORD A, METZ L, CHINTALA S, et al. Unsupervised Re-presentation Learning with Deep Convolutional Generative Adversa-rial Networks[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1511.06434.pdf.
[15] RUDER S. An Overview of Multi-task Learning in Deep Neural Networks[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1706.05098.pdf.
[16] ZHANG Y, YANG Q. An Overview of Multi-task Learning. National Science Review, 2018, 5: 30-43.
[17] VN TRAN P. Learning to Make Predictions on Graphs with Autoencoders[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1802.08352.pdf.
[18] TANG L, LIU H. Leveraging Social Media Networks for Classification. Data Mining and Knowledge Discovery, 2011, 23(3): 447-478.
[19] KIPF T N, WELLING M. Variational Graph Auto-Encoders[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1611.07308.pdf.
[20] PAN S R, HU R Q, FUNG S F, et al. Learning Graph Embedding with Adversarial Training Methods[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1901.01250.pdf.
[21] LU Q, GETOOR L. Link-Based Classification // Proc of the 20th International Conference on Machine Learning. New York, USA: ACM, 2003: 496-503.
[22] YANG Z L, COHEN W W, SALAKHUTDINOV R, et al. Revisiting Semi-supervised Learning with Graph Embeddings[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1603.08861.pdf.
[23] ZHOU T, LU L Y, ZHANG Y G. Predicting Missing Links via Local Information. The European Physical Journal B, 2009, 71(4): 623-630.
[24] PAN S R, HU R Q, LONG G D, et al. Adversarially Regularized Graph Autoencoder for Graph Embedding[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1802.04407.pdf.
[25] LIU P F, QIU X P, HANG X J, et al. Recurrent Neural Network for Text Classification with Multi-Task Learning[C/OL]. [2019-07-20]. https://arxiv.org/pdf/1605.05101.pdf.