Neighbor Relation-Aware Graph Convolutional Network for Recommendation

doi:10.3778/j.issn.1002-8331.2112-0438

Abstract

Abstract: Existing recommender systems based on graph neural networks mainly aggregate the information of neighbors indiscriminately when updating the representation of the target node. In this way, most useful prior knowledge is not introduced in combination with the recommendation system itself to distinguish the relationship between users and items. To solve this problem, a neighbor relation-aware graph convolutional network（NRGCN） is proposed, which combines three prior auxiliary information of rating score, review text, and the timestamp to distinguish the expression differences of different neighbors in the neighborhood explicitly. Specifically, the user’s rating score is introduced as the basis for the closeness of the network, which is then modified by the sentiment score of the review text. Besides, considering the changes in the user’s interest over time, the timestamp is used to encode the neighbor relationship at different times. Extensive experiments on three benchmark datasets show that the proposed model outperforms various state-of-the-art models consistently, with a maximum increase of 12%.

Key words: graph neural network, neighbor relation, review text, sentiment score, timestamp

摘要： 现有的基于图神经网络的推荐模型在更新目标节点向量时大多对邻居节点信息进行无差别的聚合，没有结合推荐系统本身引入更多有用的先验知识，从而区分目标节点与不同邻居节点之间的关系。针对此问题，提出一种基于邻居关系感知的图卷积网络推荐模型（neighbor relation-aware graph convolutional network，NRGCN），分别引入评分数值、评论文本和评分时间三种先验辅助信息实现对邻居节点的多层次聚合。具体来讲，以用户对物品的真实评分数值作为网络中不同邻居关系紧密程度的基础，利用评论文本的情感倾向对邻居关系进行修正补充，最后考虑到用户的兴趣随时间的变化情况，使用评分时间来标记不同时间交互下的邻居关系。在3组公开的数据集上，NRGCN的召回率高于多个基准算法，最大提高了12%。

关键词: 图神经网络, 邻居关系, 评论文本, 情感倾向, 评分时间

SUN Aijing, WANG Guoqing. Neighbor Relation-Aware Graph Convolutional Network for Recommendation[J]. Computer Engineering and Applications, 2023, 59(9): 112-122.

孙爱晶, 王国庆. 邻居关系感知的图卷积网络推荐模型[J]. 计算机工程与应用, 2023, 59(9): 112-122.

References

[1] GRBOVIC M，RADOSAVLJEVIC V，DJURIC N，et al.Ecommerce in your inbox：product recommendations at scale[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，Sydney，Australis，2015：1809-1818.
[2] CHIEN T C，CHEN Z H，CHAN T W.Exploring long-term behavior patterns in a book recommendation system for reading[J].Journal of Educational Technology & Society，2017，20（2）：27-36.
[3] JAMALI M，ESTER M.A matrix factorization technique with trust propagation for recommendation in social networks[C]//Proceedings of the Fourth ACM Conference on Recommender Systems，2010：135-142.
[4] HE X，LIAO L，ZHANG H，et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web，Perth，Australia，2017：173-182.
[5] KOREN Y，BELL R，VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer，2009，42（8）：30-37.
[6] MNIH A，SALAKHUTDINOV R R.Probabilistic matrix factorization[C]//Advances in Neural Information Processing Systems，2008：1257-1264.
[7] WANG X，HE X，WANG M，et al.Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval，Paris，France，2019：165-174.
[8] KIPF T N，WELLING M.Semi-supervised classification with graph convolutional networks[J].arXiv：1609.02907，2016.
[9] HAMILTON W L，YING R，LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Prcessing Systems，2017：1025-1035.
[10] SUN J，ZHANG Y，GUO W，et al.Neighbor interaction aware graph convolution networks for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，2020：1289-1298.
[11] BERG R，KIPF T N，WELLING M.Graph convolutional matrix completion[J].arXiv：1706.02263，2017.
[12] WU C，WU F，QI T，et al.Reviews meet graphs：enhancing user and item representations for recommendation with hierarchical attentive graph neural network[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing（EMNLP-IJCNLP），Hong Kong，China，2019：4886-4895.
[13] ZHANG M，WU S，YU X，et al.Dynamic graph neural networks for sequential recommendation[J].arXiv：2104. 07368，2021.
[14] HU Z，ZHENG X，WU Y，et al.Product recommendation algorithm based on users’ reviews mining[J].Journal of Zhejiang University（Engineering Science），2013，47（8）：1475-1485.
[15] GORI M，PUCCI A，ROMA V，et al.Itemrank：a random-walk based scoring algorithm for recommender engines[C]//Proceedings of the 20th International Joint Conference on Artificial Intelligence，2007：2766-2771.
[16] VELI?KOVI? P，CUCURULL G，CASANOVA A，et al.Graph attention networks[J].arXiv：1710.10903，2017.
[17] YING R，HE R，CHEN K，et al.Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，2018：974-983.
[18] SUN J，ZHANG Y，MA C，et al.Multi-graph convolution collaborative filtering[C]//2019 IEEE International Conference on Data Mining（ICDM），2019：1306-1311.
[19] HE X，DENG K，WANG X，et al.LightGCN：simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，Virtual Event，China，2020：639-648.
[20] WANG X，WANG R，SHI C，et al.Multi-component graph convolutional collaborative filtering[C]//Proceedings of the AAAI Conference on Artificial Intelligence，New York，USA，2020，34（4）：6267-6274.
[21] ZHU H，FENG F，HE X，et al.Bilinear graph neural network with neighbor interactions[J].arXiv：2002.03575，2020.
[22] SONG J，CHANG C，SUN F，et al.NGAT4Rec：neighbor-aware graph attention network for recommendation[J].arXiv：2010.12256，2020.
[23] WANG X，JIN H，ZHANG A，et al.Disentangled graph collaborative filtering[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval，2020：1001-1010.
[24] SOCHER R，PERELYGIN A，WU J，et al.Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing，Washington，USA，2013：1631-1642.
[25] DEVLIN J，CHANG M W，LEE K，et al.Bert：pre-training of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[26] RENDLE S，FREUDENTHALER C，GANTNER Z，et al.BPR：Bayesian personalized ranking from implicit feed-back[J].arXiv：1205.2618，2012.
[27] KINGMA D P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[28] ZHANG Y，SHI Z，ZUO W，et al.Joint personalized Markov chains with social network embedding for cold-start recommendation[J].Neurocomputing，2020，386：208-220.