[1]朱金侠,孟祥福,邢长征,等.融合图卷积注意力机制的协同过滤推荐方法[J].智能系统学报,2023,18(6):1295-1304.[doi:10.11992/tis.202203039]
ZHU Jinxia,MENG Xiangfu,XING Changzheng,et al.Collaborative filtering recommendation approach fused with graph convolutional attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18(6):1295-1304.[doi:10.11992/tis.202203039]
点击复制
ZHU Jinxia,MENG Xiangfu,XING Changzheng,et al.Collaborative filtering recommendation approach fused with graph convolutional attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18(6):1295-1304.[doi:10.11992/tis.202203039]
融合图卷积注意力机制的协同过滤推荐方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第6期
页码:
1295-1304
栏目:
学术论文—人工智能基础
出版日期:
2023-11-05
- Title:
- Collaborative filtering recommendation approach fused with graph convolutional attention mechanism
- Keywords:
- graph embedding technology; graph convolutional network; attention mechanism; collaborative filtering; user preference; collaborative filtering; high-order interaction; neighbor aggregation
- 分类号:
- TP311
- 摘要:
- 图卷积神经网络(graph convolutional neural network, GCN)因其强大的建模能力引起了广泛关注,在商品推荐中，现有的图卷积协同过滤技术忽略了邻居节点在传播聚合过程中的重要性，使得用户和商品的嵌入向量表达不够合理。为了解决这一问题，本文提出一种融合图卷积注意力机制的协同过滤推荐模型。首先通过图嵌入技术将用户-项目的交互信息映射到低维稠密的向量空间；其次通过堆叠多层的图卷积网络学习用户与项目间的高阶交互信息；同时融合注意力机制为邻居节点自适应地分配权重，不仅可以捕获更具代表性的邻居影响，还使得在聚合邻居节点的特征信息时，仅依赖于节点之间的特征表达，使其独立于图结构，提高了模型的泛化能力；最后设计了分层聚合函数，将图卷积层学习到的多个嵌入向量加权聚合，使用内积函数得到用户-项目之间的关联分数。在3个真实数据上进行的泛化实验，实验结果验证了该方法的有效性。
- Abstract:
- The graph convolutional neural network (GCN) has attracted extensive attention due to its powerful modeling capabilities. In item recommendation, existing graph convolution collaborative filtering techniques ignore the importance of neighbor nodes in the propagation aggregation process, making the embedding vector representation of user and item unreasonable. Therefore, this paper proposes a collaborative filtering recommendation model fused with graph convolutional attention to address this problem. First, user-item interaction information was mapped to a low-dimensional, dense vector space using graph embedding techniques. Further, the high-order interaction information between the user and the item was learned using stacking multiple layers of GCN. The model also fused attention mechanisms to adaptively assign weights to neighbor nodes, thereby capturing the influence of highly representative neighbors. Simultaneously, the model could rely only on feature expressions between nodes when aggregating feature information from neighboring nodes, increasing the independence of the graph structure and improving the generalization capability of the model. Finally, a hierarchical aggregation function that aggregated multiple embedding vectors, which was learned from the graph convolution layer by weighting, was designed, and the inner product function was used to obtain the association score between the user and the item. Results of the extensive experiments conducted on three real datasets have demonstrated the effectiveness of the proposed approach.
- 参考文献/References:
-
[1] SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web. New York: ACM, 2001: 285-295.
[2] AMBULGEKAR H P, PATHAK M K, KOKARE M B. A survey on collaborative filtering: tasks, approaches and applications[C]//Proceedings of International Ethical Hacking Conference 2018. Singapore: Springer, 2019: 289-300.
[3] SUN Guangfu, WU Le, LIU Qi, et al. Recommendations based on collaborative filtering by exploiting sequential behaviors[J]. Journal of software, 2014, 24(11): 2721–2733.
[4] HE Xiangnan, LIAO Lizi, ZHANG Hanwang, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web. New York: ACM, 2017: 173-182.
[5] SHUMAN D I, NARANG S K, FROSSARD P, et al. The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains[C]//IEEE Signal Processing Magazine. New York: IEEE, 2013: 83-98.
[6] YING R, HE Ruining, CHEN Kaifeng, et al. Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2018: 974-983.
[7] WANG Xiang, HE Xiangnan, WANG Meng, et al. Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019: 165-174.
[8] HE Xiangnan, DENG Kuan, WANG Xiang, et al. LightGCN: simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 639-648.
[9] KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer journal, 2009, 42(8): 30–37.
[10] KOREN Y. Factorization meets the neighborhood: a multifaceted collaborative filtering model[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2008: 426-434.
[11] HE Xiangnan, DU Xiaoyu, WANG Xiang, et al. Outer product-based neural collaborative filtering[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 2227-2233.
[12] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 701-710.
[13] GROVER A, LESKOVEC J. Node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 855-864.
[14] GORI M, PUCCI A. ItemRank: a random-walk based scoring algorithm for recommender engines[C]//Proceedings of the 20th International Joint Conference on Artificial Intelligence. New York: ACM, 2007: 2766-2771.
[15] CHEN C M, TSAI M F, LIN Y C, et al. Query-based music recommendations via preference embedding[C]//Proceedings of the 10th ACM Conference on Recommender Systems. New York: ACM, 2016: 79-82.
[16] YANG J H, CHEN C M, WANG Chuanju, et al. HOP-rec: high-order proximity for implicit recommendation[C]//Proceedings of the 12th ACM Conference on Recommender Systems. New York: ACM, 2018: 140-144.
[17] 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. New York: ACM, 2017: 1025-1035.
[18] XU Yanan, ZHU Yanmin, SHEN Yanyan, et al. Learning shared vertex representation in heterogeneous graphs with convolutional networks for recommendation[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2019: 4620-4626.
[19] PETAR V, GUILLEM C, ARANTXA C, et al. Graph attention networks[C]//Proceedings of International Conference on Learning Representations. Vancouver: ICLR, 2018, 23-35.
[20] 王宏琳, 杨丹, 聂铁铮, 等. 自注意力机制的属性异构信息网络嵌入的商品推荐[J]. 计算机研究与发展, 2022, 59(7): 1509–1521
WANG Honglin, YANG Dan, NIE Tiezheng, et al. Attributed heterogeneous information network embedding with self-attention mechanism for product recommendation[J]. Journal of computer research and development, 2022, 59(7): 1509–1521
[21] LIU Donghua, LI Jing, DU Bo, et al. DAML: dual attention mutual learning between ratings and reviews for item recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019: 344-352.
[22] 高海燕, 毛林, 窦凯奇, 等. 基于图嵌入模型的协同过滤推荐算法[J]. 数据采集与处理, 2020, 35(3): 483–493
GAO Haiyan, MAO Lin, DOU Kaiqi, et al. Graph embedding model based collaborative filtering algorithm[J]. Journal of data acquisition and processing, 2020, 35(3): 483–493
[23] 邢长征, 赵宏宝, 张全贵, 等. 融合评论文本层级注意力和外积的推荐方法[J]. 计算机科学与探索, 2020, 14(6): 947–957
XING Changzheng, ZHAO Hongbao, ZHANG Quangui, et al. Review text hierarchical attention and outer product for recommendation method[J]. Journal of frontiers of computer science and technology, 2020, 14(6): 947–957
[24] MAAS A L. Rectifier nonlinearities improve neural network acoustic models[C]//Proceedings of International Conference on Machine Learning. New York: ACM, 2013, 28-34.
[25] 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. New York: ACM, 2009: 452-461.
[26] VAN DEN BERG R, KIPF T, WELLING M. Graph convolutional matrix completion[C]// Proceedings of Computing Research Repository. New York: ACM, 2017, 1706-02263.
[27] KINGMA D, BA J. Adam: a method for stochastic optimization[C]//Proceedings of the International Conference on Learning Representations. San Diego: ICLR, 2015, 1412-1427.
- 相似文献/References:
-
[1]钟秋波,郑彩明,朴松昊.时空域融合的骨架动作识别与交互研究[J].智能系统学报,2020,15(3):601.[doi:10.11992/tis.202006029]
ZHONG Qiubo,ZHENG Caiming,PIAO Songhao.Research on skeleton-based action recognition with spatiotemporal fusion and human–robot interaction[J].CAAI Transactions on Intelligent Systems,2020,15():601.[doi:10.11992/tis.202006029]
[2]刘威,王薪予,刘光伟,等.融合关系特征的半监督图像分类方法研究[J].智能系统学报,2022,17(5):886.[doi:10.11992/tis.202109022]
LIU Wei,WANG Xinyu,LIU Guangwei,et al.Semi-supervised image classification method fused with relational features[J].CAAI Transactions on Intelligent Systems,2022,17():886.[doi:10.11992/tis.202109022]
[3]陈容珊,高淑萍,齐小刚.注意力机制和图卷积神经网络引导的谱聚类方法[J].智能系统学报,2023,18(5):936.[doi:10.11992/tis.202208041]
CHEN Rongshan,GAO Shuping,QI Xiaogang.A spectral clustering based on GCNs and attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18():936.[doi:10.11992/tis.202208041]
[4]周贤琛,马扬,程光权,等.战场目标实体类型识别的鲁棒图神经网络方法[J].智能系统学报,2023,18(6):1156.[doi:10.11992/tis.202111025]
ZHOU Xianchen,MA Yang,CHENG Guangquan,et al.Robust graph neural network method for target entity type recognition in a battlefield environment[J].CAAI Transactions on Intelligent Systems,2023,18():1156.[doi:10.11992/tis.202111025]
[5]曹汉童,陈璟.融合Doc2vec与GCN的多类型蛋白质相互作用预测方法[J].智能系统学报,2023,18(6):1165.[doi:10.11992/tis.202212029]
CAO Hantong,CHEN Jing.Prediction of multitype protein interactions combining Doc2vec and GCN[J].CAAI Transactions on Intelligent Systems,2023,18():1165.[doi:10.11992/tis.202212029]
备注/Memo
收稿日期:2022-3-22。
基金项目:国家重点研发计划项目（2018YFB1402901 ）；国家自然科学基金项目（61772249）；辽宁省教育厅一般项目（LJ2019QL017）.
作者简介:朱金侠,硕士研究生,主要研究方向为推荐系统;孟祥福,教授,博士,主要研究方向为Web数据库top-k查询、空间数据管理、推荐系统和大数据可视化。主持国家自然科学基金2 项,主持辽宁省各类基金项目3 项。发表学术论文60余篇, 出版学术专著1 部。;邢长征,教授,主要研究方向为分布式数据库与数据管理、流聚类、推荐系统。主持国家重点研发计划项目子课题任务1 项,省部级科研项目3 项,矿山安全应用类课题10 余项。获辽宁省优秀教学成果一等奖1 项。发表学术论文40 余篇,编写出版教材3 部。
通讯作者:孟祥福.E-mail:marxi@126.com
更新日期/Last Update:
1900-01-01