MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-Behavior Recommendation

Yan Mingshi; Chen Huilin; Cheng Zhiyong; Han Yahong

doi:10.7544/issn1000-1239.202440770

Journal of Computer Research and Development > 2025 > Accepted Manuscript > DOI: 10.7544/issn1000-1239.202440770 CSTR: 32373.14.issn1000-1239.202440770

Yan Mingshi, Chen Huilin, Cheng Zhiyong, Han Yahong. MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-Behavior Recommendation[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440770

Citation:

PDF (1845 KB)

MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-Behavior Recommendation

1.
College of Intelligence and Computing, Tianjin University, Tianjin 300354
2.
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230002

Funds: This work was supported by the National Natural Science Foundation of China (62376186, 61932009, 6227225).

More Information

Author Bio:
Yan Mingshi: born in 1989. PhD. His main research interests include artificial intelligence and personalized information recommendation

Chen Huilin: born in 1995. PhD. His main research interests include artificial intelligence and personalized information recommendation

Cheng Zhiyong: born in 1985. PhD, professor, PhD supervisor. His main research interests include multimedia information retrieval and recommendation systems

Han Yahong: born in 1977. PhD, professor, PhD supervisor. His main research interests include multimedia analysis and retrieval, computer vision, machine learning.（yahong@tju.edu.cn）
Received Date: October 09, 2024
Revised Date: March 27, 2024
Accepted Date: April 02, 2025
Available Online: April 02, 2025

Graphical Abstract

Abstract

Abstract

Collaborative filtering-based recommender systems that only rely on single-behavior data often encounter serious sparsity problems in practical applications, resulting in poor performance. Multi-behavior recommendation (MBR) is a method that seeks to learn user preferences, represented as vector embeddings, from auxiliary behavior interaction data. By leveraging these preferences for target behavior recommendations, MBR can mitigate the data sparsity challenge and enhances predictive precision for recommendations. This research introduces MB-HGCN, a novel recommendation method designed to exploit multi-behavior data. The method leverages a hierarchical graph convolutional network to learn user and item embeddings from a coarse-grained global level to a fine-grained behavior-specific level. Our method learns global embeddings from a unified homogeneous graph constructed by the interactions of all behaviors, which are then used as initialized embeddings for behavior-specific embedding learning in each behavior graph. Moreover, we also emphasize the distinct of the user and item behavior-specific embeddings and design two simple-yet-effective strategies to aggregate the behavior-specific embeddings for users and items, respectively. Finally, we adopt multi-task learning for optimization. Extensive experimental results on three real-world benchmark datasets show that our MB-HGCN method can substantially outperform the state-of-the-art methods, achieving a relative improvement of 73.93% and 74.21% for HR@10 and NDCG@10, respectively, on the Tmall datasets.

FullText(HTML)

References (39)

References

[1]	Koren Y, Bell R M, Volinsky C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30−37
[2]	Rendle S, Freudenthaler C, Gantner Z, et al. BPR: Bayesian personalized ranking from implicit feedback[C]//Proc of the 25th Int Conf on Uncertainty in Artificial Intelligence. New York: ACM, 2009: 452−461
[3]	Luo Xin, Zhou Mengchu, Li Shuai, et al. A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(3): 579−592
[4]	Xi Wudong, Huang Ling, Wang Changdong, et al. Deep rating and review neural network for item recommendation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(11): 6726−6736
[5]	Ni Juan, Huang Zhenhua, Yu Chang, et al. Comparative convolutional dynamic multi-attention recommendation model[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 3510−3521
[6]	张劲羽,马晨曦,李超,等. 基于三分支图外部注意力网络的轻量化跨域序列推荐[J]. 计算机研究与发展,2024,61(8):1930−1944 doi: 10.7544/issn1000-1239.202440197 Zhang Jinyu, Ma Chenxi, Li Chao, et al. Towards lightweight cross-domain sequential recommendation via tri-branches graph external attention network[J]. Journal of Computer Research and Development, 2024, 61(8): 1930−1944 (in Chinese) doi: 10.7544/issn1000-1239.202440197
[7]	王磊,熊于宁,李云鹏,等. 一种基于增强图卷积神经网络的协同推荐模型[J]. 计算机研究与发展,2021,58(9):1987−1996 doi: 10.7544/issn1000-1239.2021.20200617 Wang Lei, Xiong Yuning, Li Yunpeng, et al. A collaborative recommendation model based on enhanced graph convolutional neural network[J]. Journal of Computer Research and Development, 2021, 58(9): 1987−1996 (in Chinese) doi: 10.7544/issn1000-1239.2021.20200617
[8]	Berg R V D, Kipf T N, Welling M. Graph convolutional matrix completion[C/OL]//Proc of the 24th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2018[2025-02-20]. https://www.kdd.org/kdd2018/files/deep-learning-day/DLDay18_paper_32.pdf
[9]	Cheng Zhiyong, Han Sai, Liu Fan, et al. Multi-behavior recommendation with cascading graph convolution networks[C]//Proc of the 32nd ACM Web Conf. New York: ACM, 2023: 1181−1189
[10]	Xia Lianghao, Huang Chao, Xu Yong, et al. Multi-behavior enhanced recommendation with cross-interaction collaborative relation modeling[C]//Proc of the 37th IEEE Int Conf on Data Engineering. Piscataway, NJ: IEEE, 2021: 1931−1936
[11]	Gao Chen, He Xiangnan, Gan Dahua, et al. Learning to recommend with multiple cascading behaviors[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(6): 2588−2601
[12]	Xia Lianghao, Huang Chao, Xu Yong, et al. Multiplex behavioral relation learning for recommendation via memory augmented transformer network[C]//Proc of the 43rd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2020: 2397−2406
[13]	Jin Bowen, Gao Chen, He Xiangnan, et al. Multi-behavior recommendation with graph convolutional networks[C]//Proc of the 43rd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2020: 659−668
[14]	Yan Mingshi, Cheng Zhiyong, Gao Chen, et al. Cascading residual graph convolutional network for multi-behavior recommendation[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 42(1): 10: 1−10: 26
[15]	Meng Chang, Zhao Ziqi, Guo Wei, et al. Coarse-to-fine knowledge-enhanced multi-interest learning framework for multi-behavior recommendation[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 42(1): 30: 1−30: 27
[16]	Zhao Zhe, Cheng Zhiyuan, Hong Lichan, et al. Improving user topic interest profiles by behavior factorization[C]//Proc of the 24th Int Conf on World Wide Web. New York: ACM, 2015: 1406−1416
[17]	Ding Jingtao, Yu Guanghui, He Xiangnan, et al. Improving implicit recommender systems with view data[C/OL]//Proc of the 27th Int Joint Conf on Artificial Intelligence. 2018: 3343−3349[2025-02-20]. https://doi.org/10.24963/ijcai.2018/464
[18]	Guo Guibing, Qiu Huihuai, Tan Zhenhua, et al. Resolving data sparsity by multi-type auxiliary implicit feedback for recommender systems[J]. Knowledge-Based Systems, 2017, 138: 202−207
[19]	Qiu Huihuai, Liu Yun, Guo Guibing, et al. BPRH: Bayesian personalized ranking for heterogeneous implicit feedback[J]. Information Sciences, 2018, 453: 80−98
[20]	Guo Long, Hua Lifeng, Jia Rongfei, et al. Buying or browsing?: Predicting real-time purchasing intent using attention-based deep network with multiple behavior[C]//Proc of the 25th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2019: 1984−1992
[21]	Xia Lianghao, Xu Yong, Huang Chao, et al. Graph meta network for multi-behavior recommendation[C]//Proc of the 44th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2021: 757−766
[22]	Gu Shuyun, Wang Xiao, Shi Chuan, et al. Self-supervised graph neural networks for multi-behavior recommendation[C/OL]//Proc of the 31st Int Joint Conf on Artificial Intelligence. 2022: 2052−2058[2025-02-20]. https://www.ijcai.org/proceedings/2022/285
[23]	Yan Mingshi, Liu Fan, Sun Jing, et al. Behavior-contextualized item preference modeling for multi-behavior recommendation[C]//Proc of the 47th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2024: 946−955
[24]	Xu Jingcao, Wang Chaokun, Wu Cheng, et al. Multi-behavior self-supervised learning for recommendation[C]//Proc of the 46th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2023: 496−505
[25]	黄玲,黄镇伟,黄梓源,等. 图卷积宽度跨域推荐系统[J]. 计算机研究与发展,2024,61(7):1713−1729 doi: 10.7544/issn1000-1239.202330617 Huang Ling, Huang Zhenwei, Huang Ziyuan, et al. Graph convolutional broad cross-domain recommender system[J]. Journal of Computer Research and Development, 2024, 61(7): 1713−1729 (in Chinese) doi: 10.7544/issn1000-1239.202330617
[26]	赵容梅,孙思雨,鄢凡力,等. 基于对比学习的多兴趣感知序列推荐系统[J]. 计算机研究与发展,2024,61(7):1730−1740 doi: 10.7544/issn1000-1239.202330622 Zhao Rongmei, Sun Siyu, Yan Fanli, et al. Multi-interest aware sequential recommender system based on contrastive learning[J]. Journal of Computer Research and Development, 2024, 61(7): 1730−1740 (in Chinese) doi: 10.7544/issn1000-1239.202330622
[27]	李挺,金福生,李荣华,等. Light-HGNN:用于圈层内容推荐的轻量同质超图神经网络[J]. 计算机研究与发展,2024,61(4):877−888 doi: 10.7544/issn1000-1239.202220643 Li Ting, Jin Fusheng, Li Ronghua, Wang Guoren, et al. Light-HGNN: lightweight homogeneous hypergraph neural network for circle content recommendation[J]. Journal of Computer Research and Development, 2024, 61(4): 877−888 (in Chinese) doi: 10.7544/issn1000-1239.202220643
[28]	Yue Guowei, Xiao Rui, Zhao Zhongying, et al. AF-GCN: Attribute-fusing graph convolution network for recommendation[J]. IEEE Transactions on Big Data, 2023, 9(2): 597−607
[29]	He Xiangnan, Deng Kuan, Wang Xiang, et al. LightGCN: Simplifying and powering graph convolution network for recommendation[C]//Proc of the 43rd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2020: 639−648
[30]	Mao Kelong, Zhu Jieming, Xiao Xi, et al. UltraGCN: Ultra simplification of graph convolutional networks for recommendation[C]//Proc of the 30th ACM Int Conf on Information and Knowledge Management. New York: ACM, 2021: 1253−1262
[31]	Wang Xiang, He Xiangnan, Cao Yixin, et al. KGAT: Knowledge graph attention network for recommendation[C]//Proc of the 25th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2019: 950−958
[32]	Qiao Pengpeng, Zhang Zhiwei, Li Zhetao, et al. TAG: Joint triple-hierarchical attention and GCN for review-based social recommender system[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 9904−9919
[33]	Ma Ting, Huang Longtao, Lu Qianqian, et al. KR-GCN: Knowledge-aware reasoning with graph convolution network for explainable recommendation[J]. ACM Transactions on Intelligent Systems and Technology, 2023, 41(1): 4: 1−4: 27
[34]	Wang Jihu, Shi Yuliang, Yu Han, et al. A novel KG-based recommendation model via relation-aware attentional GCN[J]. Knowledge-Based Systems, 2023, 275: 110702
[35]	Liu Han, Wei Yinwei, Yin Jianhua, et al. HS-GCN: Hamming spatial graph convolutional networks for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(6): 5977−5990
[36]	Hu Pengqing, Lin Zhaohao, Pan Weike, et al. Privacy-preserving graph convolution network for federated item recommendation[J]. Artificial Intelligence, 2023, 324: 103996
[37]	Peng Shaowen, Sugiyama K, Mine T. SVD-GCN: A simplified graph convolution paradigm for recommendation[C]//Proc of the 31st ACM Int Conf on Information and Knowledge Management. New York: ACM, 2022: 1625−1634
[38]	Schlichtkrull M S, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[C]//Proc of the 15th European Semantic Web Conf. Berlin: Springer, 2018: 593−607
[39]	Xia Lianghao, Huang Chao, Xu Yong, et al. Multi-behavior graph neural networks for recommender system[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(4): 5473−5487

[1]	Qian Zhongsheng, Huang Heng, Zhu Hui, Liu Jinping. Multi-Perspective Graph Contrastive Learning Recommendation Method with Layer Attention Mechanism[J]. Journal of Computer Research and Development, 2025, 62(1): 160-178. DOI: 10.7544/issn1000-1239.202330804
[2]	Li Siheng, Jin Beihong, Zhang Fusang, Wang Zhi, Ma Junqi, Su Chang, Ren Xiaoyong, Liu Haiqin. Multi-Task Attention Network for Contactless Sleep Monitoring[J]. Journal of Computer Research and Development, 2024, 61(11): 2739-2753. DOI: 10.7544/issn1000-1239.202440389
[3]	Cao Zelin, Xu Jun, Dong Zhenhua, Wen Jirong. Prediction of the Positional Propensity Scores Based on Multi Task Learning[J]. Journal of Computer Research and Development, 2023, 60(1): 85-94. DOI: 10.7544/issn1000-1239.202110853
[4]	Lai Xinyu, Chen Si, Yan Yan, Wang Dahan, Zhu Shunzhi. Survey on Deep Learning Based Facial Attribute Recognition Methods[J]. Journal of Computer Research and Development, 2021, 58(12): 2760-2782. DOI: 10.7544/issn1000-1239.2021.20200870
[5]	Liu Zhuang, Liu Chang, Wayne Lin, Zhao Jun. Pretraining Financial Language Model with Multi-Task Learning for Financial Text Mining[J]. Journal of Computer Research and Development, 2021, 58(8): 1761-1772. DOI: 10.7544/issn1000-1239.2021.20210298
[6]	Zhou Hang, Zhan Yongzhao, Mao Qirong. Video Anomaly Detection Based on Space-Time Fusion Graph Network Learning[J]. Journal of Computer Research and Development, 2021, 58(1): 48-59. DOI: 10.7544/issn1000-1239.2021.20200264
[7]	Qin Tao, Shen Zhuang, Liu Huan, Chen Zhouguo. Learning to Rank for Evolution Trend Evaluation of Online Public Opinion Events[J]. Journal of Computer Research and Development, 2020, 57(12): 2490-2500. DOI: 10.7544/issn1000-1239.2020.20200725
[8]	Xing Xinying, Ji Junzhong, Yao Yao. Brain Networks Classification Based on an Adaptive Multi-Task Convolutional Neural Networks[J]. Journal of Computer Research and Development, 2020, 57(7): 1449-1459. DOI: 10.7544/issn1000-1239.2020.20190186
[9]	Qin Chenguang, Wang Hai, Ren Jie, Zheng Jie, Yuan Lu, Zhao Zixin. Dialect Language Recognition Based on Multi-Task Learning[J]. Journal of Computer Research and Development, 2019, 56(12): 2632-2640. DOI: 10.7544/issn1000-1239.2019.20190101
[10]	Wang Jun, Wei Jinmao, Zhang Lu. Multi-Task Feature Learning Algorithm Based on Preserving Classification Information[J]. Journal of Computer Research and Development, 2017, 54(3): 537-548. DOI: 10.7544/issn1000-1239.2017.20150963