Recommendation method based on multidimensional social relationship embedded deep graph neural network

doi:10.11772/j.issn.1001-9081.2020040569

Abstract

Abstract: The social recommendation system can alleviate the data sparsity and cold start problems in the recommendation system through the users' social attribute information, thereby improving the accuracy of the recommendation system. However, most social recommendation methods mainly aim at the single social network or linearly superimpose multiple social networks, making it difficult for the users' social attributes to fully participate in the calculation, so the accuracy of recommendation is limited. To solve this problem, a multi-network embedded graph neural network model was proposed to implement the recommendation in complex multidimensional social networks. In the model, a unified method was built to fuse the multidimensional complex networks composed of user-item, user-user and other relationships. Different types of multi-neighbors were aggregated to attribute to the node generation through attention mechanism, and multiple graph neural networks were combined to construct a graph neural network recommendation framework under multidimensional social relationships. In the proposed method, the entities in the recommendation system and their relationships were reflected by the topology structure, and the relevant information was calculated and updated continuously on the graph directly. It can be seen that the method is inductive, and avoids the problem of incomplete information utilization in traditional recommendation methods effectively. By comparing with related social recommendation algorithms, the experimental results show that the recommendation accuracy indicators such as Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the proposed method are improved, and the method even has good accuracy on sparse data.

Key words: multi-dimensional social network, social recommendation, graph neural network, multi-layer perceptron, network embedding

摘要： 社会化推荐系统通过用户的社会属性信息能缓解推荐系统中数据稀疏性和冷启动问题，从而提高推荐系统的精度。然而大多数社会化推荐方法主要针对单一的社交网络，或对多个社交网络进行线性叠加，使得用户社会属性难以充分参与计算，因而推荐的精度有限。针对该问题，提出一种多重网络嵌入的图形神经网络模型来实现复杂多维社交网络下的推荐，该模型构建了统一的方法来融合用户-物品、用户-用户等各种关系构成的多维复杂网络，通过注意力机制聚合不同类型的多邻居对节点生成作出贡献，并将多个图神经网络进行组合，从而构建了多维社交关系下的图神经网络推荐框架。这种方法通过拓扑结构直接反映推荐系统中实体及其相互间关系，直接在图上对相关信息进行不断更新计算，具有很强的归纳性，有效避免了传统推荐方法中信息利用不完全的问题。通过与相关的社会推荐算法进行比较，实验结果表明，所提方法在均方根误差（RMSE）和平均绝对误差（MAE）等推荐精度指标上有所改善，甚至在数据稀疏情况下也有良好的精度。

CLC Number:

TP391

HE Haochen, ZHANG Danhong. Recommendation method based on multidimensional social relationship embedded deep graph neural network[J]. Journal of Computer Applications, 2020, 40(10): 2795-2803.

何昊晨, 张丹红. 基于多维社交关系嵌入的深层图神经网络推荐方法[J]. 计算机应用, 2020, 40(10): 2795-2803.

References

[1] 孟祥武, 刘树栋, 张玉洁, 等. 社会化推荐系统研究[J]. 软件学报,2015,26(6):1356-1372.(MENG X W,LIU S D,ZHANG Y J,et al. Research on social recommender systems[J]. Journal of Software,2015,26(6):1356-1372.)
[2] YANG X,GUO Y,LIU Y,et al. A survey of collaborative filtering based social recommender systems[J]. Computer Communications, 2014,41:1-10.
[3] DEBNATH S,GANGULY N,MITRA P. Feature weighting in content based recommendation system using social network analysis[C]//Proceedings of the 17th International Conference on World Wide Web. New York:ACM,2008:1041-1042.
[4] ECK D,LAMERE P,BERTIN-MAHIEUX T,et al. Automatic generation of social tags for music recommendation[C]//Proceedings of the 20th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2007:385-392.
[5] YANG X,STECK H,LIU Y. Circle-based recommendation in online social networks[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:1267-1275.
[6] CHUN H,KWAK H,EOM Y H,et al. Comparison of online social relations in volume vs interaction:a case study of cyworld[C]//Proceedings of the 8th ACM SIGCOMM Conference on Internet Measurement. New York:ACM,2008:57-70.
[7] OU M,CUI P,WANG F,et al. Comparing apples to oranges:a scalable solution with heterogeneous hashing[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2013:230-238.
[8] SHEN J,PANG H,WANG M,et al. Modeling concept dynamics for large scale music search[C]//Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM,2012:455-464.
[9] SHEN J,CHENG Z. Personalized video similarity measure[J]. Multimedia Systems,2011,17(5):421-433.
[10] FENG H, QIAN X. Mining user-contributed photos for personalized product recommendation[J]. Neurocomputing, 2014,129:409-420.
[11] BELÉM F M,ALMEIDA J M,GONÇALVES M A. A survey on tag recommendation methods[J]. Journal of the Association for Information Science and Technology,2017,68(4):830-844.
[12] XIA B,LI T,LI Q,et al. Noise-tolerance matrix completion for location recommendation[J]. Data Mining and Knowledge Discovery,2018,32(1):1-24.
[13] LIU J, TANG M, ZHENG Z, et al. Location-aware and personalized collaborative filtering for Web service recommendation[J]. IEEE Transactions on Services Computing,2016,9(5):686-699.
[14] YANG X,STECK H,LIU Y. Circle-based recommendation in online social networks[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:1267-1275.
[15] JIANG M, CUI P, LIU R, et al. Social contextual recommendation[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management. New York:ACM,2012:45-54.
[16] SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[C]//Proceedings of the 20th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2007:1257-2364.
[17] HUANG Z,LIU Q,ZHAI C,et al. Exploring multi-objective exercise recommendations in online education systems[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York:ACM, 2019:1261-1270.
[18] ZHENG N,SONG S,BAO H. A temporal-topic model for friend recommendations in Chinese microblogging systems[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2015, 45(9):1245-1253.
[19] LU Y,ZHAO L,WANG B. From virtual community members to C2C e-commerce buyers:trust in virtual communities and its effect on consumers' purchase intention[J]. Electronic Commerce Research and Applications,2010,9(4):346-360.
[20] YUAN Q,CHEN L,ZHAO S. Factorization vs. regularization:fusing heterogeneous social relationships in top-n recommendation[C]//Proceedings of the 5th ACM conference on Recommender Systems. New York:ACM,2011:245-252.
[21] KIM H R,CHAN P K. Learning implicit user interest hierarchy for context in personalization[C]//Proceedings of the 8th International Conference on Intelligent User Interfaces. New York:ACM,2003:101-108.
[22] 李琳, 刘锦行, 孟祥福, 等. 融合评分矩阵与评论文本的商品推荐模型[J]. 计算机学报,2018,41(7):1559-1573.(LI L,LIU J H,MENG X F,et al. Recommendation models by exploiting rating matrix and review text[J]. Chinese Journal of Computers, 2018,41(7):1559-1573.)
[23] 张宜浩, 朱小飞, 徐传运, 等. 基于用户评论的深度情感分析和多视图协同融合的混合推荐方法[J]. 计算机学报,2019,42(6):1316-1333.(ZHANG Y H,ZHU X F,XU C Y,et al. Hybrid recommendation approach based on deep sentiment analysis of user reviews and multi-view collaborative fusion[J]. Chinese Journal of Computers,2019,42(6):1316-1333.)
[24] ZHAO G,QIAN X,XIE X. User-service rating prediction by exploring social users' rating behaviors[J]. IEEE Transactions on Multimedia,2016,18(3):496-506.
[25] HUANG S, ZHANG J, WANG L, et al. Social friend recommendation based on multiple network correlation[J]. IEEE Transactions on Multimedia,2016,18(2):287-299.
[26] YU W,LI S. Recommender systems based on multiple social networks correlation[J]. Future Generation Computer Systems, 2018,87:312-327.
[27] PENG H,WANG H,DU B,et al. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting[J]. Information Sciences,2020,521:277-290.
[28] LI M,MA Z,WANG Y G,et al. Fast Haar transforms for graph neural networks[J]. Neural Networks,2020,128:188-198.
[29] ZOU F, SHEN L, JIE Z, et al. A sufficient condition for convergences of Adam and RMSProp[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:11119-11127.
[30] GUO G,ZHANG J,YORKE-SMITH N. TrustSVD:collaborative filtering with both the explicit and implicit influence of user trust and of item ratings[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2015:123-129.
[31] TANG J,AGGARWAL C,LIU H. Recommendations in signed social networks[C]//Proceedings of the 25th International Conference on World Wide Web. Republic and Canton of Geneva, CHE:International World Wide Web Conferences Steering Committee,2016:31-40.