计算机科学 ›› 2021, Vol. 48 ›› Issue (4): 104-110.doi: 10.11896/jsjkx.200800027

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于多层次多视角的图注意力Top-N推荐方法

刘志鑫, 张泽华, 张杰   

  1. 太原理工大学信息与计算机学院 太原030024
  • 收稿日期:2020-06-24 修回日期:2020-10-01 出版日期:2021-04-15 发布日期:2021-04-09
  • 通讯作者: 张泽华(zehua_zhang@163.com)
  • 基金资助:
    国家自然科学基金项目(61503273,61702356);教育部产学合作协同育人项目;山西省回国留学人员科研资助项目

Top-N Recommendation Method for Graph Attention Based on Multi-level and Multi-view

LIU Zhi-xin, ZHANG Ze-hua, ZHANG Jie   

  1. School of Information and Computer,Taiyuan University of Technology,Taiyuan 030024,China
  • Received:2020-06-24 Revised:2020-10-01 Online:2021-04-15 Published:2021-04-09
  • About author:LIU Zhi-xin,born in 1996,postgradua-te.His main research interests include recommendation system and knowledge discovery on graph.(itsliuzhixin@163.com)
    ZHANG Ze-hua,born in 1981,Ph.D,master supervisor,is a member of China Computer Federation.His main research interests include granular computing,uncertain reasoning and knowledge discovery on graph.
  • Supported by:
    National Natural Science Foundation of China(61503273,61702356),Industry-University Cooperation Education Program of the Ministry of Education and Shanxi Scholarship Council of China.

摘要: 推荐系统是当前数据挖掘领域的研究热点,海量数据的涌现促使多源信息融合的推荐方法得到极大的关注。但是,现有的基于异质信息融合的推荐方法在进行特征表示时往往忽略了用户和项目之间的交互信息以及元路径之间的相互影响。因此,考虑到属性节点嵌入和结构元路径的不同视角,提出了一种多层次图注意力的网络推荐方法。该方法通过构建不同的元路径,将多源信息网络结构粒化为多个独立的粗粒度网络,然后基于图注意力机制结合局部节点属性嵌入,来分别学习用户和项目的潜在特征,最终给出融合后的细粒度网络推荐。在现实大规模数据集上进行横向和纵向评测,实验结果表明该方法能够有效地提升推荐性能。

关键词: Top-N推荐, 层次粒化, 多源信息融合, 图注意力网络

Abstract: Recommendation system is a research hotspot in the field of data mining.Due to the emergence of massive data,the reco-mmendation methodsof multi-source information fusion receive great attention.However,the existing recommendation methods based on heterogeneous information fusion often ignore the interaction information between users and items,as well as the interaction between meta-paths in feature representation.Therefore,considering the influence of different perspectives of attribute node embedding and structural meta-paths,a network recommendation method with multi-level graph attention is proposed.This method granulates the multi-source information network structure into multiple independent coarse-grained networks by constructing different meta-paths.Then,based on graph attention mechanism and local node attribute embedding,this method can learn the potential features of users and items separately.Finally,it gives a fine-grained network recommendation after fusion.The horizontal and vertical evaluations are conducted on real large-scale data sets,and the experimental results show that this method can effectively improve the recommendation performance.

Key words: Graph attention network, Hierarchical granulation, Multi-source information fusion, Top-N recommendation

中图分类号: 

  • TP183
[1]SHI C,HU B,ZHAO W X,et al.Heterogeneous information network embedding for recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2018,31(2):357-370.
[2]ZHU J,ZHANG J,ZHANG C,et al.CHRS:Cold startrecommendation across multiple heterogeneous information networks[J].IEEE Access,2017,5:15283-15299.
[3]WANG X,HOI S C H,ESTER M,et al.Learning personalized preference of strong and weak ties for social recommendation[C]//Proceedings of the 26th International Conference on World Wide Web.2017:1601-1610.
[4]ZHANG J,LI T,JIANG Z,et al.A Novel Weighted Meta Graph Method for Classification in Heterogeneous Information Networks[J].Applied Sciences,2020,10(5):1603.
[5]CHEN Y,WANG C.HINE:Heterogeneous information net-work embedding[C]//Proceedings of the International Conference on Database Systems for Advanced Applications.Springer,Cham,2017:180-195.
[6]ZHAO H,YAO Q,LI J,et al.Meta-graph based recommendation fusion over heterogeneous informationnetworks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:635-644.
[7]SHI C,ZHANG Z,LUO P,et al.Semantic path based personalized recommendation on weighted heterogeneous information networks[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.2015:453-462.
[8]HU B,SHI C,ZHAO W X,et al.Leveraging meta-path basedcontext for top-n recommendation with a neural co-attention model[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:1531-1540.
[9]苗夺谦,王国胤,刘清,等.粒计算:过去,现在与展望[M].北京:科学出版社,2007.
[10]ZADEHL A.Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic[J].Fuzzy Sets and Systems,1997,90(2):111-127.
[11]HU Q H,YU D R,XIE Z X.Numerical attribute reductionbased on neighborhood granulation and rough approximation[J].Journal of Software,2008,19(3):640-649.
[12]QIAN Y,LIANG X,WANG Q,et al.Local rough set:a solution to rough data analysis in big data[J].International Journal of Approximate Reasoning,2018,97:38-63.
[13]ZHAO X,ZHANG Z H,ZHANG C W,et al.RGNE:A Net-work Embedding Method for Overlapping Community Detection Based on Rough Granulation[J].Journal of Computer Research and Development,2020,57(6):1302-1311.
[14]SHI C,LIU J,ZHUANG F,et al.Integrating heterogeneous information via flexible regularization framework for recommendation[J].Knowledge and Information Systems,2016,49(3):835-859.
[15]DAI F,GU X,LI B,et al.Meta-Graph Based Attention-Aware Recommendation over Heterogeneous Information Networks[C]//Proceedings of the International Conference on Computational Science.Springer,Cham,2019:580-594.
[16]ZHANG Z W,CUI P,ZHU W W.Deep learning on graphs:A survey[J].arXiv:1812.04202v3,2020.
[17]BERG R,KIPF T N,WELLING M.Graph convolutional matrixcompletion[C]//Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2018.
[18]ZHENG L,LU C T,JIANG F,et al.Spectral collaborative filtering[C]//Proceedings of the 12th ACM Conference on Recommender Systems.2018:311-319.
[19]PENG H,LI J,GONG Q,et al.Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.IJCAI,2019:3238-3245.
[20]WANG X,JI H,SHI C,et al.Heterogeneous Graph Attention Network[C]//Proceedings of the World Wide Web Conference.ACM,2019:2022-2032.
[21]FAN S,ZHU J,HAN X,et al.Metapath-guided heterogeneous graph neural network for intent recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:2478-2486.
[22]SUN Y,HAN J,YAN X,et al.Pathsim:Meta path-based top-k similarity search in heterogeneous information networks[J].Proceedings of the VLDB Endowment,2011,4(11):992-1003.
[23]VELIKOVI P,CUCURULL G,CASANOVA A,et al.Graph attention networks[C]//Proceedings of the 6th International Conference on Learning Representations.ICLR,2018.
[24]HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.2017:173-182.
[25]KINGMA D P,BA J.Adam:a method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representations.ICLR,2015.
[26]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.Bpr:Bayesian personalized ranking from implicit feedback[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence.UAI,2009:452-461.
[1] 史殿习, 赵琛然, 张耀文, 杨绍武, 张拥军.
基于多智能体强化学习的端到端合作的自适应奖励方法
Adaptive Reward Method for End-to-End Cooperation Based on Multi-agent Reinforcement Learning
计算机科学, 2022, 49(8): 247-256. https://doi.org/10.11896/jsjkx.210700100
[2] 秦琪琦, 张月琴, 王润泽, 张泽华.
基于知识图谱的层次粒化推荐方法
Hierarchical Granulation Recommendation Method Based on Knowledge Graph
计算机科学, 2022, 49(8): 64-69. https://doi.org/10.11896/jsjkx.210600111
[3] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[4] 曾伟良, 陈漪皓, 姚若愚, 廖睿翔, 孙为军.
时空图注意力网络在交叉口车辆轨迹预测的应用
Application of Spatial-Temporal Graph Attention Networks in Trajectory Prediction for Vehicles at Intersections
计算机科学, 2021, 48(6A): 334-341. https://doi.org/10.11896/jsjkx.200800066
[5] 杜少华, 万怀宇, 武志昊, 林友芳.
融合文本序列和图信息的海关商品HS编码分类
Customs Commodity HS Code Classification Integrating Text Sequence and Graph Information
计算机科学, 2021, 48(4): 97-103. https://doi.org/10.11896/jsjkx.200900053
[6] 张良成, 王运锋.
动态自适应的多雷达信息加权融合方法
Dynamic Adaptive Multi-radar Tracks Weighted Fusion Method
计算机科学, 2020, 47(11A): 321-326. https://doi.org/10.11896/jsjkx.2004000145
[7] 徐朝辉,廉飞宇,付麦霞.
多智能代理决策交互的博弈问题研究
Study on Game Theory in Decision Interaction for Multi Intelligent Agents Based on Information Fusion
计算机科学, 2013, 40(7): 196-200.
[8] 胡振涛,刘宇,杨树军.
多传感器量测下权重优化粒子滤波算法
Weights Optimization Particle Filter Algorithm in Multi-sensor Measurement
计算机科学, 2013, 40(12): 152-155.
[9] 巫茜,蔡海尼,黄丽丰.
基于主成分分析的多源特征融合故障诊断方法
Feature-level Fusion Fault Diagnosis Based on PCA
计算机科学, 2011, 38(1): 268-270.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!