GCN-MF: A graph convolutional network based on matrix factorization for recommendation

Junxi Yang; Zongshui Wang; Chong Chen

doi:10.61187/ita.v2i1.30

Authors

Junxi Yang School of Computing, Beijing Information Science and Technology University, Beijing 100096, China
Zongshui Wang
wangzongshui8@163.com
School of Economics and Management, Beijing Information Science and Technology University, Beijing 100096, China
Chong Chen School of Computing, Beijing Information Science and Technology University, Beijing 100096, China

Keywords:

Recommendation Systems, Graph Convolutional Network, Deep Learning, Matrix Factorization

Abstract

With the increasing development of information technology and the rise of big data, the Internet has entered the era of information overload. While users enjoy the convenience brought by big data to their daily lives, they also face more and more information filtering and selection problems. In this context, recommendation systems have emerged, and existing recommendation systems cannot effectively deal with the problem of data sparsity. Therefore, this paper proposes a graph convolutional network based on matrix factorization for recommendation. The embedding layer uses matrix factorization instead of neighborhood aggregation, and the interaction layer uses multi-layer neural networks instead of simple inner products. Finally, on the Movielens-1M, Yelp and Gowalla public data set, NDCG and Recall are better than the existing baseline model, which effectively alleviates the data sparsity problem.

Downloads

Download data is not yet available.

References

Hanafi, M., Suryana, N., Bin, S., et al. Paper survey and example of collaborative filtering implementation in recommender system. Journal of Theoretical and Applied Information Technology, 2017, 3195(16), 4001-4014.

Ye, X., Yuan, P., Guo, X., et al. Collaborative filtering recommendation algorithm based on user interest and project cycle. Journal of Nanjing University of Science and Technology, 2018, 42(4), 392-400. https://doi.org/10.14177/j.cnki.32-1397n.2018.42.04.002

Sarwar, B., Karypis, G., Konstan, J., et al. Analysis of recommendation algorithms for e-commerce. In proceedings of the 2nd ACM Conference on Electronic Commerce, 2000: 158-167. https://doi.org/10.1145/352871.352887 DOI: https://doi.org/10.1145/352871.352887

Sedhain, S., Menon, A. K., Sanner, S., Xie, L. AutoRec: Autoencoders Meet Collaborative Filtering. In proceedings of the 24th International Conference on World Wide Web, 2015, 111-112. https://doi.org/10.1145/2740908.2742726 DOI: https://doi.org/10.1145/2740908.2742726

Ying, S., Hoens, T. R., Jian, J., et al. Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features. In proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 255-62. https://doi.org/10.1145/2939672.2939704 DOI: https://doi.org/10.1145/2939672.2939704

Qu, Y., Han, C. Product-Based Neural Networks for User Response Prediction. In proceedings of 2016 IEEE 16th International Conference on Data Mining (ICDM), 2016, 1149-5. https://doi.org/10.1109/ICDM.2016.0151 DOI: https://doi.org/10.1109/ICDM.2016.0151

Cheng, H-T., KOC, L., Harmsen, J., et al. Wide & deep learning for recommender systems. In proceedings of the 1st workshop on deep learning for recommender systems, 2016, 7-10. https://doi.org/10.1145/3041021.3054227 DOI: https://doi.org/10.1145/2988450.2988454

Zhu, H., Li, X., Zhang, P., et al. Learning tree-based deep model for recommender systems. In proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 1079-1088. https://doi.org/10.1145/3219819.3219826 DOI: https://doi.org/10.1145/3219819.3219826

Wu, Z., Pan, S., Chen, F., et al. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(1),4-24. https://doi.org/10.1109/TNNLS.2020.2978386 DOI: https://doi.org/10.1109/TNNLS.2020.2978386

Ying, R., He, R., Chen, K., et al. Graph convolutional neural networks for web-scale recommender systems. In proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2018, 974-983. https://doi.org/10.1145/3219819.3219890 DOI: https://doi.org/10.1145/3219819.3219890

Wang, M., Lin, Y., Lin, G., et al. M2GRL: A multi-task multi-view graph representation learning framework for web-scale recommender systems. In proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 2020, 2349-2358. https://doi.org/10.1145/3394486.3403284 DOI: https://doi.org/10.1145/3394486.3403284

Huang, Z., Lin, Z., Gong, Z., et al. A two‐phase knowledge distillation model for graph convolutional network‐based rec-ommendation. International Journal of Intelligent Systems, 2022, 37(9), 5902-5923. https://doi.org/10.1002/int.22819 DOI: https://doi.org/10.1002/int.22819

Chen, L., Bi, X., Fan, G., et al. A multitask recommendation algorithm based on DeepFM and Graph Convolutional Network. Concurrency and Computation: Practice and Experience, 2023, e7498. https://doi.org/10.1002/cpe.7498 DOI: https://doi.org/10.1002/cpe.7498

He, X., Zhang, H., Kan, M.Y., et al. Fast matrix factorization for online recommendation with implicit feedback. In pro-ceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. 2016, 549-558. https://doi.org/10.1145/2911451.2911489 DOI: https://doi.org/10.1145/2911451.2911489

Li, C., Che, H., Leung M.F., et al. Robust multi-view non-negative matrix factorization with adaptive graph and diversity constraints. Information Sciences, 2023, 634: 587-607. https://doi.org/10.1109/CCBD.2016.012 DOI: https://doi.org/10.1016/j.ins.2023.03.119

Wang, S., Zhang, Y., Lin, X., et al. Learning matrix factorization with scalable distance metric and regularizer. Neural Net-works, 2023, 161, 254-266. https://doi.org/10.1016/j.neunet.2023.01.034 DOI: https://doi.org/10.1016/j.neunet.2023.01.034

Salakhutdinov, R., Mnih, A. Probabilistic matrix factorization. In proceedings of the 20th International Conference on Neural Information Processing Systems, 2007, 1257–1264.

Kipf, T. N., Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016. https://doi.org/10.1109/ACCESS.2021.3060173 DOI: https://doi.org/10.1109/ACCESS.2021.3060173

Wang, X., He, X., Wang, M., et al. Neural graph collaborative filtering. In proceedings of the 42nd international ACM SIGIR conference on Research and development in Information Retrieval. 2019, 165-174. https://doi.org/10.1145/3331184.3331267 DOI: https://doi.org/10.1145/3331184.3331267

Liu, K., Xue, F., Hong, R. RGCF: Refined graph convolution collaborative filtering with concise and expressive embedding. Intelligent Data Analysis, 2022, 26(2), 427-445. https://doi.org/10.3233/IDA-205725 DOI: https://doi.org/10.3233/IDA-205725

Chen, L., Wu, L., Hong, R., et al. Revisiting graph based collaborative filtering: A linear residual graph convolutional network approach. In proceedings of the AAAI conference on artificial intelligence. 2020, 34(01), 27-34. https://doi.org/10.1609/aaai.v34i01.5330 DOI: https://doi.org/10.1609/aaai.v34i01.5330

He, X., Deng, K., Wang, X., et al. Lightgcn: Simplifying and powering graph convolution network for recommendation. In proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval. 2020, 639-648. https://doi.org/10.1145/3397271.3401063 DOI: https://doi.org/10.1145/3397271.3401063

Jin, R., Li, D., Gao, J., et al. Towards a better understanding of linear models for recommendation. In proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021, 776-785. https://doi.org/10.1145/3447548.3467428 DOI: https://doi.org/10.1145/3447548.3467428

Li, Q., Han, Z., Wu, X. Deeper insights into graph convolutional networks for semi-supervised learning. In proceedings of the AAAI conference on artificial intelligence. 2018, 32(1),3528-3538. https://doi.org/10.48550/arXiv.1801.07606 DOI: https://doi.org/10.1609/aaai.v32i1.11604

Risi, I. K. Diffusion kernels on graphs and other discrete input spaces. In Proceedings of the 19th International Conference on Machine Learning, 2002, 315-322.

He, X., Liao, L., Zhang, H., et al. Neural collaborative filtering. In proceedings of the 26th International Conference on World Wide Web. 2017, 173-182. https://doi.org/10.1145/3038912.3052569 DOI: https://doi.org/10.1145/3038912.3052569

Hornik, K., Stinchcombe, M., White, H. Multilayer feedforward networks are universal approximators. Neural networks, 1989, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8 DOI: https://doi.org/10.1016/0893-6080(89)90020-8

He, R., McAuley, J. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web. 2016: 507-517. https://doi.org/10.1145/2872427.2883037 DOI: https://doi.org/10.1145/2872427.2883037

Rendle, S., Freudenthaler, C., Gantner, Z., et al. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618, 2012. https://doi.org/10.48550/arXiv.1205.2618

Mao, K., Zhu, J., Xiao, X., et al. UltraGCN: ultra simplification of graph convolutional networks for recommendation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 2021: 1253-1262. https://doi.org/10.1145/3459637.3482291 DOI: https://doi.org/10.1145/3459637.3482291