基于多视图集成的网络表示学习算法
|
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。
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.
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.
引文
[1]TSOUMKAS G,KATAKIS I,TANIAR D.Multi-label classification:an overview[J].International Journal of Data Warehousing&Mining,2007,3(3):1-13.
[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.
[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.
[4]YU X,REN X,SUN Y,et al.Personalized entity recommendation:a heterogeneous information network approach[C]∥ACMInternational Conference on Web Search and Data Mining.NY:ACM,2014:283-292.
[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.
[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.
[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.
[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.
[9]CHEN Y,PEROZZI B,SKIENA S.Vector-based similarity measurements for historical figures[M]∥Similarity Search and Applications.Berlin:Springer,2015.
[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.
[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.
[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.
[13]YANG C,LIU Z Y,ZHAO D L,et al.Network representation learning with rich text information[C]∥International Conference on Artificial Intelligence.Palo Alto:AAAI,2015:2111-2117.
[14]NATARAJAN N,DHILLON I S.Inductive matrix completion for predicting gene-disease associations[J].Bioinformatics,2014,30(12):60-68.
[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.
[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.
[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.
[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.
[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.AAAIPress,2017:3894-3900.
[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.
[21]MAATEN L V D,HINTON G.Visualizing Data using t-SNE[J].Journal of Machine Learning Research,2008,9:2579-2605.
[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.
[23]GROVER A,LESKOVEC J.node2vec:Scalable Feature Learning for Networks[C]∥the 22nd ACM SIGKDD International Conference.NY:ACM,2016:855-864.
[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.
[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.
[4]YU X,REN X,SUN Y,et al.Personalized entity recommendation:a heterogeneous information network approach[C]∥ACMInternational Conference on Web Search and Data Mining.NY:ACM,2014:283-292.
[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.
[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.
[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.
[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.
[9]CHEN Y,PEROZZI B,SKIENA S.Vector-based similarity measurements for historical figures[M]∥Similarity Search and Applications.Berlin:Springer,2015.
[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.
[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.
[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.
[13]YANG C,LIU Z Y,ZHAO D L,et al.Network representation learning with rich text information[C]∥International Conference on Artificial Intelligence.Palo Alto:AAAI,2015:2111-2117.
[14]NATARAJAN N,DHILLON I S.Inductive matrix completion for predicting gene-disease associations[J].Bioinformatics,2014,30(12):60-68.
[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.
[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.
[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.
[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.
[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.AAAIPress,2017:3894-3900.
[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.
[21]MAATEN L V D,HINTON G.Visualizing Data using t-SNE[J].Journal of Machine Learning Research,2008,9:2579-2605.
[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.
[23]GROVER A,LESKOVEC J.node2vec:Scalable Feature Learning for Networks[C]∥the 22nd ACM SIGKDD International Conference.NY:ACM,2016:855-864.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |