计算机科学 ›› 2019, Vol. 46 ›› Issue (1): 117-125.doi: 10.11896/j.issn.1002-137X.2019.01.018

• 2018 年第七届中国数据挖掘会议 • 上一篇    下一篇

基于多视图集成的网络表示学习算法

冶忠林1, 赵海兴1,2, 张科2, 朱宇2   

  1. (陕西师范大学计算机科学学院 西安710062)1
    (青海师范大学计算机学院 西宁810008)2
  • 收稿日期:2018-05-05 出版日期:2019-01-15 发布日期:2019-02-25
  • 作者简介:冶忠林(1989-),男,博士生,CCF会员,主要研究方向为自然语言处理;赵海兴(1969-),男,博士,教授,主要研究方向为复杂网络、自然语言处理,E-mail:h.x.zhao@163.com(通信作者);张 科(1986-),男,博士生,主要研究方向为复杂网络;朱 宇(1986-),男,博士生,主要研究方向为复杂网络。
  • 基金资助:
    国家自然科学基金支持项目(61663041,61763041),长江学者和创新研究团队项目(IRT_15R40),中国教育部春辉计划研究基金项目(Z2014022),青海省自然科学基金项目(2013-Z-Y17,2014-ZJ-721),中央高校基本科研业务费专项资金(2017TS045)资助

Network Representation Learning Based on Multi-view Ensemble Algorithm

YE Zhong-lin1, ZHAO Hai-xing1,2, ZHANG Ke2, ZHU Yu2   

  1. (School of Computer Science,Shaanxi Normal University,Xi’an 710062,China)1
    (College of Computer,Qinghai Normal University,Xining 810008,China)2
  • Received:2018-05-05 Online:2019-01-15 Published:2019-02-25

摘要: 现有的网络表示学习算法主要为基于浅层神经网络的网络表示学习和基于神经矩阵分解的网络表示学习。基于浅层神经网络的网络表示学习又被证实是分解网络结构的特征矩阵。另外,现有的大多数网络表示学习仅仅从网络的结构学习特征,即单视图的表示学习;然而,网络本身蕴含有多种视图。因此,文中提出了一种基于多视图集成的网络表示学习算法(MVENR)。该算法摈弃了神经网络的训练过程,将矩阵的信息融合和分解思想融入到网络表示学习中。另外,将网络的结构视图、连边权重视图和节点属性视图进行了有效的融合,弥补了现有网络表示学习中忽略了网络连边权重的不足,解决了基于单一视图训练时网络特征稀疏的问题。实验结果表明,所提MVENR算法的性能优于网络表示学习中部分常用的联合学习算法和基于结构的网络表示学习算法,是一种简单且高效的网络表示学习算法。

关键词: 表示学习, 复杂网络编码学习, 网络表示学习, 网络可视化, 网络嵌入学习

Abstract: The existing network representation learning algorithms mainly consist of the methods based on the shallow neural network and the approaches based on neural matrix factorization.It has been proved that network representation learning based on shallow neural network is to factorize feature matrix of network structure.In addition,most of the existing network representation algorithms learn the features from the structure information,which is a single view representation learning for networks.However,there are various kinds of views in the network.Therefore,this paper proposed a network representation learning approach based on multi-view ensemble (MVENR).The algorithm abandons the neural network training process and integrates the idea of matrix information ensemble and factorization into the network representation vectors.MVENR gives effective combination strategy between the network structure view.The link weight view and the node attribute view.Meanwhile,it makes up the shortage of neglecting the network link weight,and solves the sparse network feature problem for using single view training.The experimental results show that the proposed algorithm outperforms the commonly joint learning algorithms and the methods purely based on network structure features,and it is a simple and efficient network representation learning algorithm.

Key words: Complex network encoding learning, Network embedding learning, Network representation learning, Network visualization, Representation learning

中图分类号: 

  • TP391
[1]TSOUMKAS G,KATAKIS I,TANIAR D.Multi-label classification:an overview [J].International Journal of Data Warehousing & Mining,2007,3(3):1-13.<br /> [2]LIBENNOWELL D,KLEINBERY J.The link-prediction problem for social networks [J].Journal of the Association for Information Science and Technology,2007,58(7):1019-1031.<br /> [3]ZHAO W X,HUANG J,WEN J R.Learning distributed representations for recommender systems with a network Embedding approach[C]//Asia Information Retrieval Symposium.Berlin:Springer,2016:224-236.<br /> [4]YU X,REN X,SUN Y,et al.Personalized entity recommendation:a heterogeneous information network approach [C]//ACM International Conference on Web Search and Data Mining.NY:ACM,2014:283-292.<br /> [5]PEROZZI B,AI-RFOU R,SKIENA S.DeepWalk:Online Learning of Social Representations [C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.NY:ACM,2014:701-710.<br /> [6]PAN S,WU J,ZHU X,et al.Tri-party deep network representation [C]//International Joint Conference on Artificial Intelligence.NY:ACM,2016:1895-1901.<br /> [7]LI Q,LIU D.Research of music recommendation system based on user behavior analysis and word2vec user emotion extraction [C]//International Conference on Intelligent and Interactive Systems and Applications.Berlin:Springer,2017:469-475.<br /> [8]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space [C]//International Conference on Learning Representations.Palo Alto:AAAI,2013:1-12.<br /> [9]CHEN Y,PEROZZI B,SKIENA S.Vector-based similarity measurements for historical figures [M]//Similarity Search and Applications.Berlin:Springer,2015.<br /> [10]LEVY O,GOLDBERY Y.Neural word embedding as implicit matrix factorization [M]//Advances in Neural Information Processing Systems.Massachusetts:MIT Press,2014:2177-2185.<br /> [11]YANG C,LIU Z.Comprehend deepwalk as matrix factorization [R/OL].(2015-01-02) [2018-01-15].http://pdfs.semanticscholar.org/0edb/7368b6f14d1b4e3a062cb2fe96e9ae50e111.pdf.<br /> [12]TU C,ZHANG W,LIU Z,et al.Max-margin deepwalk:discriminative learning of network representation [C]//International Joint Conference on Artificial Intelligence.Palo Alto:AAAI,2016:3889-3895.<br /> [13]YANG C,LIU Z Y,ZHAO D L,et al.Network representation learning with rich text information [C]//International Con-ference on Artificial Intelligence.Palo Alto:AAAI,2015:2111-2117.<br /> [14]NATARAJAN N,DHILLON I S.Inductive matrix completion for predicting gene-disease associations [J].Bioinformatics,2014,30(12):60-68.<br /> [15]KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[R/OL].(2016-09-09) [2017-12-10].http://www.ics.uci.edu/~welling/publications/papers/Submitted2016-SSL-GCNN.pdf.<br /> [16]LI J,ZHU J,ZHANG B.Discriminative deep random walk for network classification [C]//Annual Meeting of the Association for Computational Linguistics.NY:ACL,2016:1004-1013.<br /> [17]YANG Z L,COHEN W,SALAKHUTDINOV R.Revisiting semi-supervised learning with graph embeddings [C]//International Conference on Machine Learning.NY:ACM,2016:40-48.<br /> [18]WANG X,CUI P,WANG J,et al.Community preserving network embedding [R/OL].(2017-02-04) [2017-11-24].http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14589/13763.<br /> [19]YANG C,SUN M S,LIU Z Y,et al.Fast network embedding enhancement via high order proximity approximation [C]//International Joint Conference on Artificial Intelligence.AAAI Press,2017:3894-3900.<br /> [20]CHEBOTAREY P,SHAMIS E.The matrix-forest theorem and measuring relations in small social groups [J].Automation & Remote Control,2006,58(9):1505-1514.<br /> [21]MAATEN L V D,HINTON G.Visualizing Data using t-SNE [J].Journal of Machine Learning Research,2008,9:2579-2605.<br /> [22]TANG J,QU M,WANG M,et al.LINE:Large-scale information network embedding [R/OL].(2013-03-12) [2017-12-12].https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/frp0228-Tang.pdf.<br /> [23]GROVER A,LESKOVEC J.node2vec:Scalable Feature Learning for Networks [C]//the 22nd ACM SIGKDD International Conference.NY:ACM,2016:855-864.
[1] 宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲.
基于无监督集群级的科技论文异质图节点表示学习方法
Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level
计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196
[2] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[3] 黄璞, 杜旭然, 沈阳阳, 杨章静.
基于局部正则二次线性重构表示的人脸识别
Face Recognition Based on Locality Regularized Double Linear Reconstruction Representation
计算机科学, 2022, 49(6A): 407-411. https://doi.org/10.11896/jsjkx.210700018
[4] 蒋宗礼, 樊珂, 张津丽.
基于生成对抗网络和元路径的异质网络表示学习
Generative Adversarial Network and Meta-path Based Heterogeneous Network Representation Learning
计算机科学, 2022, 49(1): 133-139. https://doi.org/10.11896/jsjkx.201000179
[5] 王营丽, 姜聪聪, 冯小年, 钱铁云.
时间感知的兴趣点推荐方法
Time Aware Point-of-interest Recommendation
计算机科学, 2021, 48(9): 43-49. https://doi.org/10.11896/jsjkx.210400130
[6] 赵金龙, 赵中英.
基于异质信息网络表示学习与注意力神经网络的推荐算法
Recommendation Algorithm Based on Heterogeneous Information Network Embedding and Attention Neural Network
计算机科学, 2021, 48(8): 72-79. https://doi.org/10.11896/jsjkx.200800226
[7] 杨如涵, 戴毅茹, 王坚, 董津.
基于表示学习的工业领域人机物本体融合
Humans-Cyber-Physical Ontology Fusion of Industry Based on Representation Learning
计算机科学, 2021, 48(5): 190-196. https://doi.org/10.11896/jsjkx.200500023
[8] 钱胜胜, 张天柱, 徐常胜.
多媒体社会事件分析综述
Survey of Multimedia Social Events Analysis
计算机科学, 2021, 48(3): 97-112. https://doi.org/10.11896/jsjkx.210200023
[9] 李鑫超, 李培峰, 朱巧明.
一种基于层级信息优化的有向网络表示学习方法
Directed Network Representation Method Based on Hierarchical Structure Information
计算机科学, 2021, 48(2): 100-104. https://doi.org/10.11896/jsjkx.191200033
[10] 王雪岑, 张昱, 刘迎婕, 于戈.
基于表示学习的在线学习交互质量评价方法
Evaluation of Quality of Interaction in Online Learning Based on Representation Learning
计算机科学, 2021, 48(2): 207-211. https://doi.org/10.11896/jsjkx.201000042
[11] 富坤, 赵晓梦, 付紫桐, 高金辉, 马浩然.
基于不完全信息的深度网络表示学习方法
Deep Network Representation Learning Method on Incomplete Information Networks
计算机科学, 2021, 48(12): 212-218. https://doi.org/10.11896/jsjkx.201000015
[12] 潘雨, 邹军华, 王帅辉, 胡谷雨, 潘志松.
基于网络表示学习的深度社团发现方法
Deep Community Detection Algorithm Based on Network Representation Learning
计算机科学, 2021, 48(11A): 198-203. https://doi.org/10.11896/jsjkx.210200113
[13] 赵曼, 赵加坤, 刘金诺.
基于自我中心网络结构特征和网络表示学习的链路预测算法
Link Prediction Algorithm Based on Ego Networks Structure and Network Representation Learning
计算机科学, 2021, 48(11A): 211-217. https://doi.org/10.11896/jsjkx.201200231
[14] 纪南巡, 孙晓燕, 李祯其.
多源异构用户生成内容的融合向量化表示学习
Fusion Vectorized Representation Learning of Multi-source Heterogeneous User-generated Contents
计算机科学, 2021, 48(10): 51-58. https://doi.org/10.11896/jsjkx.200900194
[15] 樊连玺, 刘彦北, 王雯, 耿磊, 吴骏, 张芳, 肖志涛.
基于多模态表示学习的阿尔兹海默症诊断算法
Multimodal Representation Learning for Alzheimer's Disease Diagnosis
计算机科学, 2021, 48(10): 107-113. https://doi.org/10.11896/jsjkx.200900178
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!