基于邻域相似的层次粒化的网络表示学习方法

doi:10.16451/j.cnki.issn1003-6059.201906003

Abstract
Figure/Table
References (33)
Related Citation (1)

Download: PDF (1282 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

The acquisition of structural features brings higher complexity to network representation learning. Based on the idea of hierarchy, an effective method is proposed to reduce the complexity of existing network representation learning methods. The network is gradually compressed into a coarse-grained representation space via node neighborhood similarity. And the coarse-grained feature representation is learned by the existing network representation learning methods. Finally, the learned coarse-grained features are gradually refined into the node representation of the original network using the graph convolution network model. Experimental results on several datasets show that the proposed method compresses the network efficiently and quickly, and the running time of the existing algorithms is greatly reduced. For the task of node classification and link prediction, the proposed method can greatly improve the performance of the original algorithm while the granularity level is low.

Key words： Network Representation Learning Hierarchy Hierarchical Granulation Graph Convolution Network

Received: 10 May 2019

ZTFLH:

TN 929.12

About author:: (QIAN Feng, master, lecturer. His research interests include data mining and network representation learning.)(ZHANG Lei, master, lecturer. Her research interests include data mining and network representation learning.)(ZHAO Shu(Corresponding author), Ph.D., professor. Her research interests include machine learning, social network and granular computing.)(CHEN Jie, Ph.D., associate professor. Her research interests include intelligent computing, machine learning and three-way decision.)(ZHANG Yanping, Ph.D., professor. Her research interests include granular computing, machine learning and quotient space theory.)(LIU Feng, master, lecturer. His research interests include granular computing and quotient space theory.)

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	QIAN Feng
	ZHANG Lei
	ZHAO Shu
	CHEN Jie
	ZHANG Yanping
	LIU Feng

Cite this article:

QIAN Feng,ZHANG Lei,ZHAO Shu等. Network Representation Learning Method Based on Hierarchical Granulation Using Neighborhood Similarity[J]. , 2019, 32(6): 504-514.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201906003 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I6/504

[1] SHEIKH N T, KEFATO Z T, MONTRESOR A. Semi-supervised Heterogeneous Information Network Embedding for Node Classification Using 1D-CNN[C/OL]. [2019-02-25]. http://disi.unitn.it/~montreso/pubs/papers/snams18b.pdf.
[2] XU G L, WANG X K, WANG Y, et al. Edge-Nodes Representation Neural Machine for Link Prediction. Algorithms, 2019, 12(1). DOI: 10.3390/a12010012.
[3] BHATIA V, RANI R. A Distributed Overlapping Community Detection Model for Large Graphs Using Autoencoder. Future Generation Computer Systems, 2019, 94: 16-26.
[4] 涂存超,杨成,刘知远,等.网络表示学习综述.中国科学(信息科学), 2017, 47(8): 980-996.
(TU C C, YANG C, LIU Z Y, et al. Network Representation Learning: An Overview. Scientia Sinica Informationis, 2017, 47(8): 980-996.)
[5] MEYER-BRÖTZ F, SCHIEBEL E, BRECHT L. Experimental Eva-luation of Parameter Settings in Calculation of Hybrid Similarities: Effects of First- and Second-Order Similarity, Edge Cutting, and Weighting Factors. Scientometrics, 2017, 111(3): 1307-1325.
[6] ZHANG H G, KONIUSZ P. Power Normalizing Second-Order Similarity Network for Few-Shot Learning[C/OL]. [2019-02-25]. https://arxiv.org/pdf/1811.04167.pdf.
[7] SONG G F. The Role of Structure and Content in Perception of Vi-sual Similarity between Web Pages. International Journal of Human-Computer Interaction, 2011, 27(8): 793-816.
[8] ZHANG J P, DING X Y, YANG J. Revealing the Role of Node Similarity and Community Merging in Community Detection. Know-ledge Based Systems, 2019, 165: 407-419.
[9] HAJIZADEH R, AGHAGOLZADEH A, EZOJI M. Mutual Neighbors and Diagonal Loading-Based Sparse Locally Linear Embedding. Applied Artificial Intelligence, 2018, 32(5): 496-514.
[10] MA M H, DENG T Q, WANG N, et al. Semi-supervised Rough Fuzzy Laplacian Eigenmaps for Dimensionality Reduction. International Journal of Machine Learning and Cybernetics, 2019, 10(2): 397-411.
[11] 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.
[12] BRA?INSKAWS A, HAVRYLOV S, TITOV I. Embedding Words as Distributions with a Bayesian Skip-Gram Model // Proc of the 27th International Conference on Computational Linguistics. Stroudsburg, USA: ACL, 2018: 1775-1789.
[13] 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. New York, USA: ACM, 2015: 1067-1077.
[14] CAO S S, LU W, XU Q K. GraRep: Learning Graph Representations with Global Structural Information // Proc of the 24th ACM Internatio-nal Conference on Information and Knowledge Management. New York, USA: ACM, 2015: 891-900.
[15] 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.
[16] CAO S S, LU W, XU Q K. Deep Neural Networks for Learning Graph Representations // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2016: 1145-1152.
[17] FAN X N, ZHANG S W, ZHANG S Y, et al. Prediction of lncRNA-Disease Associations by Integrating Diverse Heterogeneous Information Sources with RWR Algorithm and Positive Pointwise Mutual Information. BMC Bioinformatics, 2019, 20(1): 871-883.
[18] VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. Journal of Machine Learning Research, 2010, 11: 3371-3408.
[19] KIPF T N, WELLING M. Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2019-02-25]. https://arxiv.org/pdf/1609.02907.pdf.
[20] HAMILTON W L, YING R, LESKOVEC J. Inductive Representation Learning on Large Graphs[C/OL]. [2019-02-25]. https://arxiv.org/pdf/1706.02216.pdf.
[21] WANG H W, WANG J, WANG J L, et al. GraphGAN: Graph Representation Learning with Generative Adversarial Nets[C/OL]. [2019-02-25]. https://arxiv.org/pdf/1711.08267.pdf.
[22] 赵姝,赵晖,陈洁,等.基于社团结构的多粒度结构洞占据者发现及分析.智能系统学报, 2016, 11(3): 343-351.
(ZHAO S, ZHAO H, CHEN J, et al. Recognition and Analysis of Structural Hole Spanner in Multi-granularity Based on Community Structure. CAAI Transactions on Intelligent Systems, 2016, 11(3): 343-351.)
[23] 张燕平,张铃,吴涛.不同粒度世界的描述法——商空间法.计算机学报, 2004, 27(3): 328-333.
(ZHANG Y P, ZHANG L, WU T. The Representation of Different Granular Worlds: A Quotient Space. Chinese Journal of Compu-ters, 2004, 27(3): 328-333.)
[24] 赵姝,柯望,陈洁,等.基于聚类粒化的社团发现算法.计算机应用, 2014, 34(10): 2812-2815.
(ZHAO S, KE W, CHEN J, et al. Community Detection Algorithm Based on Clustering Granulation. Journal of Computer Applications, 2014, 34(10): 2812-2815.)
[25] SARKAR P, CHAKRABARTI D, BICKEL P. The Consistency of Common Neighbors for Link Prediction in Stochastic Blockmodels // Proc of the 28th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2015, II: 3016-3024.
[26] BAG S, KUMAR S K, TIWARI M K. An Efficient Recommendation Generation Using Relevant Jaccard Similarity. Information Sciences, 2019, 483: 53-64.
[27] HAMERS L, HEMERYCK Y, HERWEYERS G, et al. Similarity Measures in Scientometric Research: The Jaccard Index Versus Salton′s Cosine Formula. Information Processing and Management, 1989, 25(3): 315-318.
[28] ADAMIC L A, LENTO T M, ADAR E, et al. Information Evolution in Social Networks // Proc of the 9th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2016: 473-482.
[29] MCCALLUM A K, NIGAM K, RENNIE J, et al. Automating the Construction of Internet Portals with Machine Learning. Information Retrieval, 2000, 3(2): 127-163.
[30] GAO H C, HUANG H. Self-paced Network Embedding // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 1406-1415.
[31] WU W, LI B, CHEN L, et al. Efficient Attributed Network Embedding via Recursive Randomized Hashing // Proc of the 27th International Joint Conference on Artificial Intelligence. Hackensack, USA: World Scientific, 2018: 2861-2867.
[32] TANG L, LIU H. Relational Learning via Latent Social Dimensions // Proc of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2009: 817-826.
[33] FAWCETT T. An Introduction to ROC Analysis. Pattern Recognition Letters, 2006, 27(8): 861-874.