Heterogeneous Network Representation Learning Based on Homogeneous Subgraghs Transformation

doi:10.19678/j.issn.1000-3428.0052645

Abstract

Abstract: Currently,most studies on information network are based on homogenous networks,while the studies on network representation learning of heterogeneous networks are relatively rare.Therefore,we propose a network representation learning algorithm,which transforms heterogeneous information networks into weighted homomorphic subgraphs according to different meta-paths.First,we construct weighted edges base on different meta-paths between similar nodes,so as to extract the weighted homogenous subgraphs from heterogeneous network.Then,we obtain the similar node sequence by random walk with offset.Finally,we use Skimp-gram model to generate the representation vector of the nodes.Experimental results show that compared with other algorithms which only consider a single meta-path,the proposed algorithm has better effects on data mining tasks such as node classification and similarity search.

Key words: network representation learning, heterogeneous network, meta path, homogeneous subgraph, random walk, Skip-gram model

摘要： 目前针对信息网络的研究多数基于同质网络，关于异质信息网络的网络表示学习研究相对较少。为此，提出一种结合不同元路径将异质信息网络转化成带权同质子图的网络表示学习算法。基于不同元路径在同类节点间构建带权重的连边，从异质网络中抽取出带权同质子图，通过带偏置的随机游走方式得到同类节点序列，并利用Skip-gram模型生成该类节点的表示向量。实验结果表明，与只考虑单一路径的算法相比，该算法处理节点分类、相似性搜索等数据挖掘任务时均能得到较好的效果。

关键词: 网络表示学习, 异质网络, 元路径, 同质子图, 随机游走, Skip-gram模型

CLC Number:

TP391.4

YIN Ying, JI Lixin, CHENG Xiaotao, HUANG Ruiyang, LIU Zhengming. Heterogeneous Network Representation Learning Based on Homogeneous Subgraghs Transformation[J]. Computer Engineering, 2019, 45(11): 204-212.

尹赢, 吉立新, 程晓涛, 黄瑞阳, 刘正铭. 基于同质子图变换的异质网络表示学习[J]. 计算机工程, 2019, 45(11): 204-212.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0052645

http://www.ecice06.com/EN/Y2019/V45/I11/204

Figures/Tables 11

References

[1] 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,USA:ACM Press,2014:701-710.
[2] GROVER A,LESKOVEC J.Node2vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:855-864.
[3] MIKOLOV T,CHEN Kai,CORRADO G,et al.Efficient estimation of word representations in vector space[EB/OL].[2018-09-01].https://arxiv.org/abs/1301.3781.
[4] SUN Yizhou,HAN Jiawei.Meta-path-based search and mining in heterogeneous information networks[J].Tsinghua Science and Technology,2013,18(4):329-338.
[5] FU Taoyang,LEE W C,LEI Zhen.HIN2Vec:explore meta-paths in heterogeneous information networks for representation learning[C]//Proceedings of 2017 ACM Conference on Information and Knowledge Management.New York,USA:ACM Press,2017:1797-1806.
[6] SUN Guolei,ZHANG Xiangliang.Graph embedding with rich information through heterogeneous network[EB/OL].[2018-09-01].https://arxiv.org/abs/1710.06879.
[7] ZHANG Jiawei,XIA Congying,ZHANG Chenwei,et al.BL-MNE:emerging heterogeneous social network embedding through broad learning with aligned autoencoder[C]//Proceedings of 2017 IEEE International Conference on Data Mining.Washington D.C.,USA:IEEE Press,2017:605-614.
[8] DONG Yuxiao,CHAWLA N,SWAMI A.Metapath2vec:scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2017:135-144.
[9] JIANG He,SONG Yangqiu,WANG Chenguang,et al.Semi-supervised learning over heterogeneous information networks by ensemble of meta-graph guided random walks[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.Melbourne,Australia:[s.n.],2017:1944-1950.
[10] SUN Yizhou,HAN Jiawei,YAN Xifeng,et al.PathSim:meta path-based top-k similarity search in heterogeneous information networks[J].Proceedings of the VLDB Endowment,2011,4(11):992-1003.
[11] SUN Yizhou,NORICK B,HAN Jiawei,et al.PathSelClus:integrating meta-path selection with user-guided object clustering in heterogeneous information networks[J].ACM Transactions on Knowledge Discovery from Data,2013,7(3):1-23.
[12] LUO Chen,GUAN Renchu,WANG Zhe,et al.HetPathMine:a novel transductive classification algorithm on heterogeneous information networks[C]//Proceedings of European Conference on Information Retrieval.Berlin,Germany:Springer,2014:210-221.
[13] 杜永萍,刘京旋,张津丽.基于多语义元路径的异质网节点分类方法[J].模式识别与人工智能,2017,30(12):1100-1107.
[14] 黄立威,李德毅,马于涛,等.一种基于元路径的异质信息网络链路预测模型[J].计算机学报,2014,37(4):848-858.
[15] RIBEIRO L F R,SAVERESE P H P,FIGUEIREDO D R.Struc2vec:learning node representations from structural identity[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2017:385-394.
[16] SUN Yizhou,HAN Jiawei.Mining heterogeneous information networks:a structural analysis approach[J].ACM SIGKDD Explorations Newsletter,2013,14(2):20-28.
[17] FOUSS F,PIROTTE A,RENDERS J M,et al.Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2007,19(3):355-369.
[18] ANDERSEN R,FAN C,LANG K.Local graph partitioning using pagerank vectors[C]//Proceedings of Symposium on Foundations of Computer Science.Washington D.C.,USA:IEEE Press,2006:475-486.
[19] BOTTOU L.Stochastic gradient learning in neural networks[J].Proceedings of Neuro Nimes,1991,91(8):12.
[20] TANG Jie,ZHANG Jing,YAO Limin,et al.Arnetminer:extraction and mining of academic social networks[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2008:990-998.
[21] MOREIRA C,CALADO P,MARTINS B.Learning to rank academic experts in the DBLP dataset[J].Expert Systems,2015,32(4):477-493.

Please choose a citation manager

Content to export