Complementary Product Recommendation Using Graph Neural Network

doi:10.3778/j.issn.1002-8331.2304-0222

Abstract

Abstract: Complementary product recommendations can provide complementary matching products for the convenience of users. However, existing work using graph neural networks ignores the multimodal information of products, and the performance of multimodal models is affected when the modal information is missing. In addition, existing multimodal models simply concatenate the modalities, ignoring the connections between the modalities. For these reasons, a complementary product recommendation using graph neural network (CPRUG) model is proposed. The model combines the graph neural network with multimodal information to strengthen the product representation. Then, it uses the graph attention network to deal with the multimodal absence problem, maintain the performance of the model, and improve the robustness of the model. Finally, it uses the common attention mechanism and matrix factorized bilinear pooling method to fuse multimodal features and learn the complementary relationship of products. Experiments are conducted on the Amazon dataset, and the experimental results show that the model outperforms other baseline models.

Key words: complementary product, graph neural network, recommendation system, multimodal

摘要： 互补产品推荐可以提供互补搭配的产品，为用户提供便利。然而现有使用图神经网络的工作忽视了产品的多模态信息，以及多模态模型在模态信息缺失时性能会受到影响。现有多模态模型只是将模态简单拼接，忽略了模态间的联系。因此，提出了一种利用图神经网络的互补产品推荐模型（complementary product recommendation using graph neural network，CPRUG）。该模型将图神经网络与多模态信息结合，强化产品的表征；利用图注意力网络，应对多模态缺失问题，维持模型的性能，提高模型的鲁棒性；使用共同注意力机制和矩阵分解双线性池化方法来融合多模态特征，学习产品的互补关系。在Amazon数据集上进行了实验，实验结果表明，模型的性能优于其他基线模型。

关键词: 互补产品, 图神经网络, 推荐系统, 多模态

NI Weijun, JI Shujuan, LIANG Yongquan. Complementary Product Recommendation Using Graph Neural Network[J]. Computer Engineering and Applications, 2024, 60(10): 292-300.

倪伟竣, 纪淑娟, 梁永全. 利用图神经网络的互补产品推荐[J]. 计算机工程与应用, 2024, 60(10): 292-300.

References

[1] BRANCO F, SUN M, VILLAS-BOAS J M. Too much information? information provision and search costs[J]. Marketing Science, 2016, 35(4): 605-618.
[2] ZHANG M, WEI X, GUO X, et al. Identifying complements and substitutes of products: a neural network framework based on product embedding[J]. ACM Transactions on Knowledge Discovery from Data, 2019, 13(3): 34.
[3] RAKESH V, WANG S, SHU K, et al. Linked variational autoencoders for inferring substitutable and supplementary items[C]//Proceedings of the 12th ACM International Conference on Web Search and Data Mining. New York: ACM, 2019: 438-446.
[4] SUN R, CAO X, ZHAO Y, et al. Multi-modal knowledge graphs for recommender systems[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 1405-1414.
[5] TAO Z, WEI Y, WANG X, et al. MGAT: multimodal graph attention network for recommendation[J]. Information Processing & Management, 2020, 57(5): 102277.
[6] LIU Y, GU Y, DING Z, et al. Decoupled graph convolution network for inferring substitutable and complementary items[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 2621-2628.
[7] HAO J, ZHAO T, LI J, et al. P-Companion: a principled framework for diversified complementary product recommendation[C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 2517-2524.
[8] ZHANG W, CHEN Z, ZHA H, et al. Learning from substitutable and complementary relations for graph-based sequential product recommendation[J]. ACM Transactions on Information Systems, 2022, 40(2): 1-28.
[9] LIU J, SONG X, NIE L, et al. An end-to-end attention-based neural model for complementary clothing matching[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2019, 15(4): 114.
[10] ZHANG Y, LU H, NIU W, et al. Quality-aware neural complementary item recommendation[C]//Proceedings of the 12th ACM Conference on Recommender Systems. New York: ACM, 2018: 77-85.
[11] XU D, RUAN C, CHO J, et al. Knowledge-aware complementary product representation learning[C]//Proceedings of the 13th International Conference on Web Search and Data Mining. New York: ACM, 2020: 681-689.
[12] MCAULEY J, PANDEY R, LESKOVEC J. Inferring networks of substitutable and complementary products[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2015: 785-794.
[13] WAN M, WANG D, LIU J, et al. Representing and recommending shopping baskets with complementarity, compatibility and loyalty[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 1133-1142.
[14] WANG R, YANG N, YU P S. Learning aspect-level complementarity for intent-aware complementary recommendation[J]. Knowledge-Based Systems, 2022, 258: 109936.
[15] YANG Z, YE J, WANG L, et al. Inferring substitutable and complementary products with knowledge-aware path reasoning based on dynamic policy network[J]. Knowledge-Based Systems, 2022, 235: 107579.
[16] WU L, ZHOU Y, ZHOU D. Towards high-order complementary recommendation via logical reasoning network[C]//Proceedings of the 2022 IEEE International Conference on Data Mining, 2022: 1227-1232.
[17] BIBAS K, SAR SHALOM O, JANNACH D. Semi-supervised adversarial learning for complementary item recommendation[C]//Proceedings of the ACM Web Conference 2023, 2023: 1804-1812.
[18] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and deep locally connected networks on graphs[C]//Proceedings of the 2nd International Conference on Learning Representations, 2014.
[19] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 1025-1035.
[20] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[21] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg: ACL, 2019: 4171-4186.
[22] PETERS M E, NEUMANN M, IYYER M, et al. Deep contextualized word representations[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Stroudsburg: ACL, 2018: 2227-2237.
[23] RADFORD A, NARASIMHAN K. Improving language understanding by generative pre-training[Z]. 2018.
[24] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[25] WANG Z, JIANG Z, REN Z, et al. A path-constrained framework for discriminating substitutable and complementary products in E-commerce[C]//Proceedings of the 11th ACM International Conference on Web Search and Data Mining. New York: ACM, 2018: 619-627.
[26] MCAULEY J, TARGETT C, SHI Q, et al. Image-based recommendations on styles and substitutes[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2015: 43-52.
[27] HE R, PACKER C, MCAULEY J. Learning compatibility across categories for heterogeneous item recommendation[C]//Proceedings of the 2016 IEEE 16th International Conference on Data Mining, 2016: 937-942.
[28] AHSAN U, CUI X, WEST R, et al. Complementary recommendations using deep multi-modal embeddings for online retail[C]//Proceedings of the 2020 IEEE International Conference on Big Data, 2020: 1774-1779.
[29] XIAO Q, LIU X, SHI H. Diversity recommendations of multi-modal complementary items[J]. Journal of Chinese Mini- Micro Computer Systems, 2021, 42(9): 1859-1864.