Graph Neural Collaborative Filtering Model Research Based on Self-Attention

SONG Yong-lei; CAO Shu-guo

doi:10.13718/j.cnki.xsxb.2021.07.019

2021 Volume 46 Issue 7

Article Contents

Previous Article Next Article

SONG Yong-lei, CAO Shu-guo. Graph Neural Collaborative Filtering Model Research Based on Self-Attention[J]. Journal of Southwest China Normal University(Natural Science Edition), 2021, 46(7): 130-134. doi: 10.13718/j.cnki.xsxb.2021.07.019

Citation:

SONG Yong-lei, CAO Shu-guo. Graph Neural Collaborative Filtering Model Research Based on Self-Attention[J]. Journal of Southwest China Normal University(Natural Science Edition), 2021, 46(7): 130-134. doi: 10.13718/j.cnki.xsxb.2021.07.019

Graph Neural Collaborative Filtering Model Research Based on Self-Attention

SONG Yong-lei¹,
CAO Shu-guo²

1.
College of Mathematics and Information Engineering, Chongqing University of Education, Chongqing 400065, China
2.
Office of Academic Affairs, Chongqing University of Education, Chongqing 400065, China

More Information

Received Date: 30/06/2020
Available Online: 20/07/2021
MSC: TP391

Abstract

Aiming at the problem that the amount of interactive coding data of the collaborative filtering signal in the collaborative filtering algorithm is too large, it is difficult to effectively obtain the required collaborative signal. The deep learning method is used here to propose a graph neural collaborative filtering model fused with self-attention (UAGNCF). First, apply the free attention mechanism to the message integration between users and projects, and then apply high-level connectivity to the embedded graph neural network layer for the processed messages, and finally aggregate the obtained messages before outputting. Experimental analysis on three data sets. The experimental results show that, compared with the existing model, its recall rate replaces other models by 5%-9%, indicating that the constructed UAGNCF model is reasonable and effective, and can obtain better recommendations effect.
- collaborative filtering,
- attention mechanism,
- high-order proximity,
- graph neural network,
- message aggregation

References

[1]	WEI S Y, YE N, ZHANG S, et al. Item-Based Collaborative Filtering Recommendation Algorithm Combining Item Category with Interestingness Measure [C]//2012 International Conference on Computer Science and Service System. Nanjing: IEEE, 2012. Google Scholar
[2]	ZHANG H W, SHEN F M, LIU W, et al. Discrete Collaborative Filtering [C]//Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. New York: ACM, 2016. Google Scholar
[3]	KOREN Y, BELL R, VOLINSKY C. Matrix Factorization Techniques for Recommender Systems [J]. Computer, 2009, 42(8): 30-37. Google Scholar
[4]	HE X N, ZHANG H W, KAN M Y, et al. Fast Matrix Factorization for Online Recommendation with Implicit Feedback [C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2016. Google Scholar
[5]	KOREN Y. Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model [C]//Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining-KDD. New York: ACM, 2008. Google Scholar
[6]	CHRISTOFFEL F, PAUDEL B, NEWELL C, et al. Blockbusters and Wallflowers: Accurate, Diverse, and Scalable Recommendations with Random Walks [C]//Proceedings of the 9th ACM Conference on Recommender Systems. New York: ACM, 2015. Google Scholar
[7]	COOPER C, LEE S H, RADZIK T, et al. Random Walks in Recommender Systems: Exact Computation and Simulations [C]//Proceedings of the 23rd International Conference on World Wide Web. New York: ACM, 2014. Google Scholar
[8]	FOUSS F, PIROTTE A, RENDERS J M, et al. Random-Walk Computation of Similarities between Nodes of a Graph with Application to Collaborative Recommendation [J]. IEEE Transactions on Knowledge and Data Engineering, 2007, 19(3): 355-369. Google Scholar
[9]	FOUSS F, PIROTTE A, SAERENS M. A Novel Way of Computing Similarities between Nodes of a Graph, with Application to Collaborative Recommendation [C]//The 2005 IEEE/WIC/ACM International Conference on Web Intelligence. Compiegne: IEEE, 2005. Google Scholar
[10]	RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian Personalized Ranking from Implicit Feedback [C]//Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. Montréal: AUAI Press, 2009. Google Scholar
[11]	HE X, LIAO L, ZHANG H, et al. Neural Collaborative Filtering [C]//Proceedings of the 26th International Conference on World Wide Web. Perth: International World Wide Web Conferences Steering Committee, 2017. Google Scholar
[12]	WANG X, HE X, WANG M, et al. Neural Graph Collaborative Filtering [C]//In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'19), Paris: ACM, 2019. Google Scholar
[13]	BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral Networks and Locally Connected Networks on Graphs [C]//International Conference on Learning Representations (ICLR2014). Banff : CBLS, 2014. Google Scholar
[14]	HAMILTON W, YING Z, LESKOVEC J. Inductive Representation Learning on Large Graphs [C]. California: Advances in Neural Information Processing Systems, 2017. Google Scholar
[15]	HENAFF M, BRUNA J, LeCun Y. Deep Convolutional Networks on Graph-Structured Data [C]. Montréal: Conference on Neural Information Processing Systems, 2015. Google Scholar
[16]	KIPF T N, WELLING M. Semi-Supervised Classification With Graph Convolutional Net-Works [C] Toulon: International Conference on Learning Representations, 2017. Google Scholar
[17]	VELICKOVIC′ P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks [C]. Vancouver: International Conference on Learning Representations, 2018. Google Scholar
[18]	YANG J H, CHEN C M, WANG C J, et al. HOP-Rec: High-Order Proximity for Implicit Recommendation [C]//Proceedings of the 12th ACM Conference on Recommender Systems. Vancouver: ACM, 2018. Google Scholar
[19]	LIANG D, CHARLIN L, MCINERNEY J, et al. Modeling User Exposure in Recommendation [C]//Proceedings of the 25th International Conference on World Wide Web. Monteral: International World Wide Web Conferences Steering Committee, 2016. Google Scholar
[20]	HARPER F M, KONSTAN J A. The MovieLens Datasets: History and Context [C]. New York: Ksii Transactions on Internet and Information Systems, 2016. Google Scholar
[21]	HE R, MCAULEY J. Ups and Downs: Modeling the Visual Evolution of Fashion Trends With One-Class Collaborative Filtering [C]//Proceedings of the 25th International Conference on World Wide Web. Montreal: International World Wide Web Conferences Steering Committee, 2016. Google Scholar

Access History

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Export Citation

PDF

XML

Article Metrics

Article views(612) PDF downloads(194) Cited by(0)

Name
	Name cannot be empty!
E-mail
	Mailbox cannot be empty! Mailbox cannot be empty!
Telephone
	Mobile number cannot be empty! Please enter a valid mobile number!
Title

Content
Verification Code

Message Board

Graph Neural Collaborative Filtering Model Research Based on Self-Attention

Abstract

References

Access History

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Access History

Other Articles By Authors