? 社会网络中基于预训练网络嵌入式表示模型的推荐算法研究
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2018, Vol. 33 Issue (4) :682-696    DOI: 10.1007/s11390-018-1849-9
Special Issue on Software Engineering for High-Confidence Systems << Previous Articles | Next Articles >>
社会网络中基于预训练网络嵌入式表示模型的推荐算法研究
Lei Guo1,2, Member, CCF, Yu-Fei Wen2, Xin-Hua Wang3
1 Postdoctoral Research Station of Management Science and Engineering, Shandong Normal University Jinan 250014, China;
2 School of Management Science and Engineering, Shandong Normal University, Jinan 250014, China;
3 School of Information Science and Engineering, Shandong Normal University, Jinan 250014, China
Exploiting Pre-Trained Network Embeddings for Recommendations in Social Networks
Lei Guo1,2, Member, CCF, Yu-Fei Wen2, Xin-Hua Wang3
1 Postdoctoral Research Station of Management Science and Engineering, Shandong Normal University Jinan 250014, China;
2 School of Management Science and Engineering, Shandong Normal University, Jinan 250014, China;
3 School of Information Science and Engineering, Shandong Normal University, Jinan 250014, China

摘要
参考文献
相关文章
Download: [PDF 5765KB]  
摘要 推荐系统作为一种有效的信息过滤技术,近年来得到了研究者们的广泛的关注。然而,传统的推荐系统研究往往仅使用用户对项目的评分信息进行推荐,而大都忽略了用户间的社会关系和项目间的序列模式。但是在实际生活中,我们总是向朋友寻求建议,并且经常选择具有相似序列模式的项目。为了解决传统方法存在的问题,许多研究者们开始考虑如何使用社会影响和序列模式影响来提高推荐系统的性能。但已有的这些研究大都将社会影响和序列模式以正则化项的方式来优化推荐的过程,隐藏在社会关系和项目序列关系中的深层次结构尚未得到充分挖掘。另一方面,基于神经网络的嵌入式表示由于能够多原始数据中提取出信息的深层次特征,在很多和推荐相关的任务上取得了较好的结果。基于以上对问题的观察,本文借鉴网络嵌入技术在表示网络特征方面的优势,提出了一种基于深层次网络嵌入特征的社会化推荐方法,该方法由嵌入表示模型和传统的协同过滤推荐模型两部分组成。具体而言,本文为了挖掘隐藏在用户间的社会关系和项目间的序列关系中的深层结构,首先在定义社会网络和序列关系网络的基础上,预先训练一个基于神经网络的网络嵌入模型,以提取其中用户和项目的网络特征表示。然后在此基础上,将这些所提取出的网络特征通过线性模型融入到传统的协同过滤模型中,使得本文的方法不仅可以利用协作过滤技术的优势保证推荐的准确性,还可以利用外部信息来进一步增强推荐的性能。在两个实际数据集上的实验结果证明了本文所提出方法的有效性,以及通过网络嵌入模式所提出的这些外部特征的重要性。
关键词社会化推荐   网络嵌入式表示   矩阵分解   项目序列模式     
Abstract: Recommender systems as one of the most efficient information filtering techniques have been widely studied in recent years. However, traditional recommender systems only utilize user-item rating matrix for recommendations, and the social connections and item sequential patterns are ignored. But in our real life, we always turn to our friends for recommendations, and often select the items that have similar sequential patterns. In order to overcome these challenges, many studies have taken social connections and sequential information into account to enhance recommender systems. Although these existing studies have achieved good results, most of them regard social influence and sequential information as regularization terms, and the deep structure hidden in social networks and rating patterns has not been fully explored. On the other hand, neural network based embedding methods have shown their power in many recommendation tasks with their ability to extract high-level representations from raw data. Motivated by the above observations, we take the advantage of network embedding techniques and propose an embedding-based recommendation method, which is composed of the embedding model and the collaborative filtering model. Specifically, to exploit the deep structure hidden in social networks and rating patterns, a neural network based embedding model is first pre-trained, where the external user and item representations are extracted. Then, we incorporate these extracted factors into a collaborative filtering model by fusing them with latent factors linearly, where our method not only can leverage the external information to enhance recommendation, but also can exploit the advantage of collaborative filtering techniques. Experimental results on two real-world datasets demonstrate the effectiveness of our proposed method and the importance of these external extracted factors.
Keywordssocial recommendation   network embedding   matrix factorization   item sequential pattern     
Received 2018-01-15;
本文基金:

This work was supported by the National Natural Science Foundation of China under Grant Nos. 61602282, 61772321, 61472231 and 71301086, and the China Postdoctoral Science Foundation under Grant No. 2016M602181.

About author: Lei Guo received his Ph.D. degree in computer architecture from Shandong University, Jinan, in 2015. Now he is a lecturer and master supervisor in the School of Management Science and Engineering, Shandong Normal University, Jinan. His research interests include information retrieval, social network, and recommender system.
引用本文:   
Lei Guo, Yu-Fei Wen, Xin-Hua Wang.社会网络中基于预训练网络嵌入式表示模型的推荐算法研究[J]  Journal of Computer Science and Technology , 2018,V33(4): 682-696
Lei Guo, Yu-Fei Wen, Xin-Hua Wang.Exploiting Pre-Trained Network Embeddings for Recommendations in Social Networks[J]  Journal of Computer Science and Technology, 2018,V33(4): 682-696
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-018-1849-9
Copyright 2010 by Journal of Computer Science and Technology