BishtRef
Articles Journals Publishers Authors Subjects Most Cited New Papers Year Stats Open Access
journal article Feb 07, 2023

Revisiting Graph-based Recommender Systems from the Perspective of Variational Auto-Encoder

Yiwen Zhang ORCID Dengcheng Yan ORCID Shuiguang Deng ORCID Yun Yang ORCID
ACM Transactions on Information Systems Vol. 41 No. 3 pp. 1-28 · Association for Computing Machinery (ACM)
View at Publisher Save 10.1145/3573385
Abstract
Graph-based recommender system has attracted widespread attention and produced a series of research results. Because of the powerful high-order connection modeling capabilities of the Graph Neural Network, the performance of these graph-based recommender systems are far superior to those of traditional neural network-based collaborative filtering models. However, from both analytical and empirical perspectives, the apparent performance improvement is accompanied with a significant time overhead, which is noticeable in large-scale graph topologies. More importantly, the intrinsic data-sparsity problem substantially limits the performance of graph-based recommender systems, which compelled us to revisit graph-based recommendation from a novel perspective. In this article, we focus on analyzing the time complexity of graph-based recommender systems to make it more suitable for real large-scale application scenarios. We propose a novel end-to-end graph recommendation model called the Collaborative Variational Graph Auto-Encoder (CVGA), which uses the information propagation and aggregation paradigms to encode user–item collaborative relationships on the user–item interaction bipartite graph. These relationships are utilized to infer the probability distribution of user behavior for parameter estimation rather than learning user or item embeddings. By doing so, we reconstruct the whole user–item interaction graph according to the known probability distribution in a feasible and elegant manner. From the perspective of the graph auto-encoder, we convert the graph recommendation task into a graph generation problem and are able to do it with approximately linear time complexity. Extensive experiments on four real-world benchmark datasets demonstrate that CVGA can be trained at a faster speed while maintaining comparable performance over state-of-the-art baselines for graph-based recommendation tasks. Further analysis shows that CVGA can effectively mitigate the data sparsity problem and performs equally well on large-scale datasets.
Topics

No keywords indexed for this article. Browse by subject →

References
58
[1]
Rianne van den Berg, Thomas N. Kipf, and Max Welling. 2017. Graph convolutional matrix completion. arXiv:1706.02263. Retrieved from https://arxiv.org/abs/1706.02263.
[3]
Chong Chen, Min Zhang, Yongfeng Zhang, Yiqun Liu, and Shaoping Ma. 2020. Efficient neural matrix factorization without sampling for recommendation. ACM Trans. Inf. Syst. 38, 2 (2020), 1–28. 10.1145/3373807
[4]
Revisiting Graph Based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

Lei Chen, Le Wu, Richang Hong et al.

Proceedings of the AAAI Conference on Artificial I... 10.1609/aaai.v34i01.5330
[6]
Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249–256.
[8]
Michael Gutmann and Aapo Hyvärinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 297–304.
[17]
Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https://arxiv.org/abs/1412.6980.
[18]
Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv:1312.6114. Retrieved from https://arxiv.org/abs/1312.6114.
[19]
Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv:1611.07308. Retrieved from https://arxiv.org/abs/1611.07308.
[20]
Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
[28]
Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. 452–461.
[35]
Jinbo Song, Chao Chang, Fei Sun, Xinbo Song, and Peng Jiang. 2020. NGAT4Rec: Neighbor-aware graph attention network for recommendation. arXiv:2010.12256. Retrieved from https://arxiv.org/abs/2010.012256.
[40]
Jakub Tomczak and Max Welling. 2018. VAE with a VampPrior. In International Conference on Artificial Intelligence and Statistics. PMLR, 1214–1223.
[42]
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations.
[47]
Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International Conference on Machine Learning. PMLR, 6861–6871.

Showing 50 of 58 references

Cited By
51
Denoising Heterogeneous Graph Pre-training Framework for Recommendation

Lei Sang, Yiwen Zhang · 2025

ACM Transactions on Information Sys...
Heterogeneous Adaptive Preference Learning for Recommendation

Lei Sang, Weichen Fei · 2025

ACM Transactions on Recommender Sys...
AdaGIN: Adaptive Graph Interaction Network for Click-Through Rate Prediction

Lei Sang, Honghao Li · 2024

ACM Transactions on Information Sys...
Dual Variational Graph Reconstruction Learning for Social Recommendation

Yiwen Zhang, Yuchuan Zhao · 2024

IEEE Transactions on Knowledge and...
Metrics
51
Citations
58
References
Details
Published
Feb 07, 2023
Vol/Issue
41(3)
Pages
1-28
License
View
Authors
Y
Yiwen Zhang

Anhui University, Hefei, Anhui Province, China

D
Dengcheng Yan

Anhui University, Hefei, Anhui Province, China

S
Shuiguang Deng

Zhejiang University, Hangzhou, Zhejiang Province, China

Y
Yun Yang

Swinburne University of Technology, Hawthorn, Melbourne, Australia

Funding
National Natural Science Foundation of China Award: 62272001, 61872002, and U1936220
Key Research and Development Plan of Anhui Province Award: 202104a05020058
Scientific Research Project for Postgraduates of Anhui Higher Education Institutions Award: YJS20210051
Cite This Article
Yiwen Zhang, Dengcheng Yan, Shuiguang Deng, et al. (2023). Revisiting Graph-based Recommender Systems from the Perspective of Variational Auto-Encoder. ACM Transactions on Information Systems, 41(3), 1-28. https://doi.org/10.1145/3573385
Related

You May Also Like

Evaluating collaborative filtering recommender systems

Jonathan L. Herlocker, Joseph A. Konstan · 2004

4,119 citations

Cumulated gain-based evaluation of IR techniques

Kalervo Järvelin, Jaana Kekäläinen · 2002

3,332 citations

Item-based top-Nrecommendation algorithms

Mukund Deshpande, George Karypis · 2004

1,700 citations

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Lei Huang, Weijiang Yu · 2025

1,105 citations

Latent semantic models for collaborative filtering

Thomas Hofmann · 2004

987 citations