Recommendation Algorithm Using Network Representation Learning Based on Random Walk

doi:10.19678/j.issn.1000-3428.0058628

Abstract

Abstract: The connections in a network can be simplified into vectors between nodes, and this vectorized representation can be applied to recommendation algorithm to improve their modeling ability.For the homogeneous networks in recommendation systems, a recommendation algorithm using Network Representation Learning(NRL) based on random walk is proposed.The algorithm is constructed based on improved DeepWalk.In the stage of random walk, the walk sequence number of the nodes is set according to the importance of the nodes.In addition, a probability of ending the walk is set to control the length of walk and optimize the sampling results.In the stage of NRL, the node attribute information is fused with the SkipGram model, and the distance between the context node and the central node is considered to improve the accuracy of recommendation results.Experimental results show that the proposed algorithm displays higher recommendation accuracy than DeepWalk, Node2vec and other algorithms.It also provides a solution to the cold-start problem.

Key words: recommendation algorithm, Network Representation Learning(NRL), random walk, sequence length, attribute information

摘要： 根据网络结构中的连接关系得到节点的向量表示，进而将节点的向量表示应用于推荐算法可有效提升其建模能力。针对推荐系统中的同质网络，提出结合随机游走的网络表示学习推荐算法。以DeepWalk算法为基础，在随机游走过程中根据节点重要性设定节点游走序列数，并设置终止概率以控制游走长度优化采样结果，在网络表示学习过程中将SkipGram模型融合节点属性信息，同时考虑上下文节点离中心节点的距离获得更准确的推荐结果。实验结果表明，该算法相比DeepWalk、Node2vec等算法具有更高的推荐准确度，并且较好地解决了冷启动问题。

关键词: 推荐算法, 网络表示学习, 随机游走, 序列长度, 属性信息

CLC Number:

TP301

LIU Feng, WANG Baoliang, ZOU Rongyu, ZHAO Haochun. Recommendation Algorithm Using Network Representation Learning Based on Random Walk[J]. Computer Engineering, 2021, 47(9): 90-96,105.

刘峰, 王宝亮, 邹荣宇, 赵浩淳. 基于随机游走的网络表示学习推荐算法[J]. 计算机工程, 2021, 47(9): 90-96,105.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0058628

http://www.ecice06.com/EN/Y2021/V47/I9/90

Figures/Tables 11

References

[1] 项亮.推荐系统实战[M].北京:人民邮电出版社, 2012. XIANG L.Recommended system practice[M].Beijing:People's Posts and Telecommunications Press, 2012.(in Chinese)
[2] RESNICK P, VARIAN H R.Recommender systems[J].Communications of the ACM, 1997, 40(3):56-58.
[3] 林霜梅, 汪更生, 陈弈秋.个性化推荐系统中的用户建模及特征选择[J].计算机工程, 2007, 33(17):196-198, 230. LIN S M, WANG G S, CHEN Y Q.User modeling and feature selection in personalized recommending system[J].Computer Engineering, 2007, 33(17):196-198, 230.(in Chinese)
[4] 毛德磊, 唐雁.基于归因理论用户偏好提取的协同过滤算法[J].计算机工程, 2019, 45(6):225-229, 236. MAO D L, TANG Y.Collaborative filtering algorithm based on attribution theory for user preference extraction[J].Computer Engineering, 2019, 45(6):225-229, 236.(in Chinese)
[5] ZHANG F Z, YUAN N J, LIAN D F, et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2016:353-362.
[6] BARKAN O, KOENIGSTEIN N.Item2vec:neural item embedding for collaborative filtering[C]//Proceedings of the 26th International Workshop on Machine Learning for Signal Processing.Washington D.C., USA:IEEE Press, 2016:1-6.
[7] ZHOU C, LIU Y, LIU X, et al.Scalable graph embedding for asymmetric proximity[C]//Proceedings of AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2017:2942-2948.
[8] 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.
[9] ROWEIS S T.Nonlinear dimensionality reduction by locally linear embedding[J].Science, 2000, 290(5500):2323-2326.
[10] BELKIN M, NIYOGI P.Laplacian eigenmaps and spectral techniques for embedding and clustering[C]//Proceedings of the 14th International Conference on Neural Information Processing Systems:Natural and Synthetic.New York, USA:ACM Press, 2002:585-591.
[11] MIKOLOV T, CHEN K, CORRADO G, et al.Efficient estimation of word representations in vector space[EB/OL].[2020-05-11].http://arxiv.org/pdf/1301.3781.
[12] SHAN Y, HOENS T R, JIAO J, et al.Deep crossing:Web-scale modeling without manually crafted combinatorial features[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2016:255-262.
[13] 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.
[14] TANG J, QU M, WANG M Z, et al.LINE:large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.Geneva, Switzerland:International World Wide Web Conferences Steering Committee, 2015:1067-1077.
[15] CAO S S, LU W, XU Q K.GraRep:learning graph representations with global structural information[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.New York, USA:ACM Press, 2015:891-900.
[16] YANG C, LIU Z, ZHAO D, et al.Network representation learning with rich text information[C]//Proceedings of International Joint Conference on Artificial Intelligence.New York, USA:ACM Press, 2015:2111-2117.
[17] PAGE L, BRIN S, MOTWANI R, et al.The PageRank citation ranking:bringing order to the Web[EB/OL].[2020-05-11].https://blog.csdn.net/iicy266/article/details/12283937.
[18] VINCENT P, LAROCHELLE H, BENGIO Y, et al.Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning.New York, USA:ACM Press, 2008:1096-1103.
[19] NG A.Sparse autoencoder[EB/OL].[2020-05-11].https://www.mendeley.com/catalogue/a06882b2-8546-33a0-9803-53cf01f649cc/.
[20] MASON S J, GRAHAM N E.Areas beneath the Relative Operating Characteristics(ROC) and Relative Operating Levels(ROL) curves:statistical significance and interpretation[J].Quarterly Journal of the Royal Meteorological Society, 2002, 128(584):2145-2166.

Please choose a citation manager

Content to export