[1]朱金侠,孟祥福,邢长征,等.融合社交关系的轻量级图卷积协同过滤推荐方法[J].智能系统学报,2022,17(4):788-797.[doi:10.11992/tis.202107031]
ZHU Jinxia,MENG Xiangfu,XING Changzheng,et al.Light graph convolutional collaborative filtering recommendation approach incorporating social relationships[J].CAAI Transactions on Intelligent Systems,2022,17(4):788-797.[doi:10.11992/tis.202107031]
点击复制
ZHU Jinxia,MENG Xiangfu,XING Changzheng,et al.Light graph convolutional collaborative filtering recommendation approach incorporating social relationships[J].CAAI Transactions on Intelligent Systems,2022,17(4):788-797.[doi:10.11992/tis.202107031]
融合社交关系的轻量级图卷积协同过滤推荐方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第4期
页码:
788-797
栏目:
学术论文—人工智能基础
出版日期:
2022-07-05
- Title:
- Light graph convolutional collaborative filtering recommendation approach incorporating social relationships
- Keywords:
- collaborative filtering; graph convolution network; attention mechanism; social relationships; recommendation system; implicit negative feedback; graph embedding; user preference
- 分类号:
- TP311
- 摘要:
- 图卷积网络(graph convolution network, GCN)因其强大的建模能力得到了迅速发展，目前大部分研究工作直接继承了GCN的复杂设计（如特征变换，非线性激活等），缺乏简化工作。另外，数据稀疏性和隐式负反馈没有被充分利用，也是当前推荐算法的局限。为了应对以上问题，提出了一种融合社交关系的轻量级图卷积协同过滤推荐模型。模型摒弃了GCN中特征变换和非线性激活的设计；利用社交关系从隐式负反馈中产生一系列的中间反馈，提高了隐式负反馈的利用率；最后，通过双层注意力机制分别突出了邻居节点的贡献值和每一层图卷积层学习向量的重要性。在2个公开的数据集上进行实验，结果表明所提模型的推荐效果优于当前的图卷积协同过滤算法。
- Abstract:
- Graph convolutional network (GCN) has rapidly developed due to their powerful modeling capability. However, much of the research up to now has directly inherited the complex design of GCN (e.g., feature transformation and nonlinear activation), which lacks thorough ablation analysis on GCN. Additionally, implicit feedback is not fully utilized, and data sparsity is not well resolved, which are also shortcomings of current recommendation algorithms. This paper proposes a light graph convolutional collaborative filtering recommendation approach that incorporates social relationships to address such problems (F-LightGCCF). In GCN, the model abandons the design of feature transformation and nonlinear activation. Then it can generate a series of intermediate feedback from users’ implicit negative feedback by taking advantage of social networking, improving the utilization of implicit negative feedback. Lastly, the importance of the contribution values of neighboring nodes and the learning vectors of each layer of the graph convolution layer are aggregated separately using the dual attention mechanism. By conducting experiments on two publicly available datasets, the results show that the proposed model outperforms current graph convolutional collaborative filtering algorithms in the recommendation.
- 参考文献/References:
-
[1] TANG Weitao, YU Dunhui, WEI Shiwei. Commodity recommendation algorithm fusing with knowledge graph and user comment[J]. Computer engineering, 2020, 46(08): 93–100.
[2] ZHANG Su, LI Hui, SHI Jun, et al. Reaearch on recommendation algorithm combining user comments and rating information[J]. Journal of shaanxi normal university, 2020, 48(02): 84–91.
[3] 印鉴, 王智圣, 李琪, 等. 基于大规模隐式反馈的个性化推荐[J]. 软件学报, 2014, 25(9): 1953–1966
YIN Jian, WANG Zhisheng, LI Qi, et al. Personalized recommendation based on large-scale implicit feedback[J]. Journal of software, 2014, 25(9): 1953–1966
[4] PETAR V, GUIKKEM C, ARANTXA C, et al. Graph attention networks. [C]//Proceedings of the 6th International Conference on Learning Representations. Vancouver: ICLR, 2018: 1710?1722.
[5] PEROZZI B, AL-RFOU R, SKIENA S. Deepwalk: online learning of social representations[C]//KDD ’14: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: ACM, 2014: 701?710.
[6] 周林娥, 游进国. 一种结合聚集图嵌入的社会化推荐算法[J]. 小型微型计算机系统, 2021, 42(1): 78-84.
ZHOU Line, YOU Jinguo. Social Recommendation with Embedding of Summarized Graphs [J]Journal of Chinese computer systems. 2021, 42(1): 78?84.
[7] 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(03): 483?493.
[8] 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.
[9] HE Xiangnan, DENG Kuan, WANG Xiang, et al. LightGCN: simplifying and powering graph convolution network for recommendation[C]//SIGIR’20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 639?648.
[10] KIPF T, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. New York: arXiv, 2016. (2016?09?09)[2021?07?17].https://arxiv.org/abs/1609.02907v4.
[11] 刘荣辉, 张敬普. 基于深度学习的正则化矩阵分解推荐系统[J]. 西南师范大学学报(自然科学版), 2021, 46(7): 103–108
LIU Ronghui, ZHANG Jingpu. Recommender system of regularization matrix decomposition based on deep learning[J]. Journal of Southwest China Normal University (natural science edition), 2021, 46(7): 103–108
[12] 吴国栋, 查志康, 涂立静, 等. 图神经网络推荐研究进展[J]. 智能系统学报, 2020, 15(1): 14–24
WU Guodong, ZHA Zhikang, TU Lijing, et al. Research advances in graph neural network recommendation[J]. CAAI transactions on intelligent systems, 2020, 15(1): 14–24
[13] 刘方爱, 王倩倩, 郝建华. 基于深度神经网络的推荐系统研究综述[J]. 山东师范大学学报(自然科学版), 2021, 36(4): 325–336
LIU Fangai, WANG Qianqian, HAO Jianhua. A survey of recommendation system based on deep neural network[J]. Journal of Shandong Normal University (natural science edition), 2021, 36(4): 325–336
[14] RIANNE Van Den Berg, THOMAS N. KIPF M W. Graph convolutional matrix completion[EB/OL]. New York: arXiv, 2017. (2017?06?07)[2021?07?17].https://arxiv.org/abs/1706.02263.
[15] YANG J H, CHEN C M, WANG Chuanju, et al. HOP-rec: high-order proximity for implicit recommendation[C]//RecSys’18: Proceedings of the 12th ACM Conference on Recommender Systems. New York: ACM, 2018: 140?144.
[16] LIU Donghua, LI Jing, DU Bo, et al. DAML: dual attention mutual learning between ratings and reviews for item recommendation[C]//KDD’19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019:344?352.
[17] XI Wudong, HUANG Ling, WANG Changdong, et al. BPAM: recommendation based on BP neural network with attention mechanism[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2019: 3905?3911.
[18] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[C]//UAI’09: Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. New York: ACM, 2009: 452?461.
[19] RAO N, YU H F, RAVIKUMAR P, et al. Collaborative filtering with graph information: consistency and scalable methods[C]//NIPS’15: Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 2. New York: ACM, 2015: 2107?2115.
[20] LIANG Dawen, KRISHNAN R G, HOFFMAN M D, et al. Variational autoencoders for collaborative filtering[C]//Proceedings of the 2018 World Wide Web Conference on World Wide Web. New York: ACM Press, 2018: 689–698.
[21] KINGMA DIEDERIK, BA JIMMY. Adam: a method for stochastic optimization. [C]//Proceedings of the International Conference on Learning Representations. San Diego: [s. n. ], 2015: 1412?1427.
[22] FU Sichao, LIU Weifeng, ZHANG Kai, et al. Semi-supervised classification by graph p-Laplacian convolutional networks[J]. Information sciences, 2021, 560: 92–106.
[23] 苏静, 许天琪, 张贤坤, 等. 基于图卷积与外积的协同过滤推荐模型[J]. 计算机应用研究, 2021, 38(10): 3044–3048
SU Jing, XU Tianqi, ZHANG Xiankun, et al. Collaborative filtering recommendation model based on graph convolution and cross product[J]. Application research of computers, 2021, 38(10): 3044–3048
- 相似文献/References:
-
[1]李慧,马小平,胡云,等.融合上下文信息的社会网络推荐系统[J].智能系统学报,2015,10(2):293.[doi:10.3969/j.issn.1673-4785.201406017]
LI Hui,MA Xiaoping,HU Yun,et al.Social network recommendaton system mixing contex information[J].CAAI Transactions on Intelligent Systems,2015,10():293.[doi:10.3969/j.issn.1673-4785.201406017]
[2]沈苗,来天平,王素美,等.北京大学课程推荐引擎的设计和实现[J].智能系统学报,2015,10(3):369.[doi:10.3969/j.issn.1673-4785.201409045]
SHEN Miao,LAI Tianping,WANG Sumei,et al.Design and implementation of the course recommendation engine in Peking University[J].CAAI Transactions on Intelligent Systems,2015,10():369.[doi:10.3969/j.issn.1673-4785.201409045]
[3]马钰,张岩,王宏志,等.面对智能导诊的个性化推荐算法[J].智能系统学报,2018,13(3):352.[doi:10.11992/tis.201711036]
MA Yu,ZHANG Yan,WANG Hongzhi,et al.A personalized recommendation algorithm for intelligent guidance[J].CAAI Transactions on Intelligent Systems,2018,13():352.[doi:10.11992/tis.201711036]
[4]陈君同,古天龙,常亮,等.融合协同过滤与用户偏好的旅游组推荐方法[J].智能系统学报,2018,13(6):999.[doi:10.11992/tis.201802011]
CHEN Juntong,GU Tianlong,CHANG Liang,et al.A tourist group recommendation method combining collaborative filtering and user preferences[J].CAAI Transactions on Intelligent Systems,2018,13():999.[doi:10.11992/tis.201802011]
[5]顾军华,谢志坚,武君艳,等.基于图游走的并行协同过滤推荐算法[J].智能系统学报,2019,14(4):743.[doi:10.11992/tis.201806002]
GU Junhua,XIE Zhijian,WU Junyan,et al.Parallel collaborative filtering recommendation algorithm based on graph walk[J].CAAI Transactions on Intelligent Systems,2019,14():743.[doi:10.11992/tis.201806002]
[6]涂飞.多特征融合的兴趣点推荐算法[J].智能系统学报,2019,14(4):779.[doi:10.11992/tis.201801048]
TU Fei.A point of interest recommendation algorithm based on multi-feature fusion[J].CAAI Transactions on Intelligent Systems,2019,14():779.[doi:10.11992/tis.201801048]
[7]张蕾,钱峰,赵姝,等.基于多粒度结构的网络表示学习[J].智能系统学报,2019,14(6):1233.[doi:10.11992/tis.201905045]
ZHANG Lei,QIAN Feng,ZHAO Shu,et al.Network representation learning based on multi-granularity structure[J].CAAI Transactions on Intelligent Systems,2019,14():1233.[doi:10.11992/tis.201905045]
[8]吴国栋,查志康,涂立静,等.图神经网络推荐研究进展[J].智能系统学报,2020,15(1):14.[doi:10.11992/tis.201908034]
WU Guodong,ZHA Zhikang,TU Lijing,et al.Research advances in graph neural network recommendation[J].CAAI Transactions on Intelligent Systems,2020,15():14.[doi:10.11992/tis.201908034]
[9]梁丽君,李业刚,张娜娜,等.融合用户特征优化聚类的协同过滤算法[J].智能系统学报,2020,15(6):1091.[doi:10.11992/tis.201710024]
LIANG Lijun,LI Yegang,ZHANG Nana,et al.Collaborative filtering algorithm combining user features and preferences in optimized clustering[J].CAAI Transactions on Intelligent Systems,2020,15():1091.[doi:10.11992/tis.201710024]
[10]王健宗,肖京,朱星华,等.联邦推荐系统的协同过滤冷启动解决方法[J].智能系统学报,2021,16(1):178.[doi:10.11992/tis.202009032]
WANG Jianzong,XIAO Jing,ZHU Xinghua,et al.Cold starts in collaborative filtering for federated recommender systems[J].CAAI Transactions on Intelligent Systems,2021,16():178.[doi:10.11992/tis.202009032]
[11]马甜甜,杨长春,严鑫杰,等.融合知识图谱和轻量级图卷积网络推荐系统的研究[J].智能系统学报,2022,17(4):721.[doi:10.11992/tis.202107016]
MA Tiantian,YANG Changchun,YAN Xinjie,et al.Research on the fusion of knowledge graph and lightweight graph convolutional network recommendation system[J].CAAI Transactions on Intelligent Systems,2022,17():721.[doi:10.11992/tis.202107016]
备注/Memo
收稿日期:2021-07-17。
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，CCF会员，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等。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，CCF会员，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，获辽宁省优秀教学成果一等奖1项。矿山安全应用类课题10余项。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