计算机科学 ›› 2021, Vol. 48 ›› Issue (8): 72-79.doi: 10.11896/jsjkx.200800226

• 数据库&大数据&数据科学* • 上一篇    下一篇

基于异质信息网络表示学习与注意力神经网络的推荐算法

赵金龙, 赵中英   

  1. 山东科技大学计算机科学与工程学院 山东 青岛266590
  • 收稿日期:2020-08-31 修回日期:2020-11-06 发布日期:2021-08-10
  • 通讯作者: 赵中英(zzysuin@163.com)
  • 基金资助:
    国家自然科学基金(62072288,61702306);山东省自然科学基金(ZR2018BF013)

Recommendation Algorithm Based on Heterogeneous Information Network Embedding and Attention Neural Network

ZHAO Jin-long, ZHAO Zhong-ying   

  1. School of Computer Science and Engineering,Shandong University of Science and Technology,Qingdao,Shandong 266590,China
  • Received:2020-08-31 Revised:2020-11-06 Published:2021-08-10
  • About author:ZHAO Jin-long,born in 1995,postgra-duate.His main research interests include network representation learning and recommendation system.(zhaojinlongchn@foxmail.com)ZHAO Zhong-ying,born in 1983,asso-ciate professor,is a senior member of China Computer Federation.Her main research interests include social network analysis and data mining.
  • Supported by:
    National Natural Science Foundation of China(62072288, 61702306) and Natural Science Foundation of Shandong Province(ZR2018BF013).

摘要: 推荐系统能够有效解决信息过载等问题,得到了国内外众多学者的广泛关注。真实世界中的应用场景往往可以建模成异质信息网络,因此基于异质信息网络表示学习的推荐算法成为了近年来的研究热点。然而,当前的研究工作仍然存在异质信息提取缺乏深度、节点的复杂关系发掘不充分等问题。为解决这些问题,文中提出了基于异质信息网络表示学习与注意力神经网络的推荐算法。首先,提出了保持语义关系与结构拓扑的异质信息网络表示方法;然后,设计了基于元路径的随机游走策略来获取异质信息网络中的节点序列,对序列过滤并生成用户和项目在不同元路径下的表示向量;最后,设计了基于注意力神经网络的推荐算法,将上述向量输入注意力神经网络,深入挖掘表示向量之间的关系以实现有效的推荐。在两个真实数据集上进行实验并与3种主流的算法进行比较,结果表明,所提算法在MAE与RMSE这2个推荐指标方面都有提升,最高提升了8.9%。

关键词: 异质信息网络, 表示学习, 元路径, 注意力神经网络, 推荐算法

Abstract: Recommendation system,as a very effective technique to solve the information overload,has received a great deal of attention from researchers.However,the real application of recommending systems can be modeled as heterogeneous networks with multi-typed nodes and relations.Thus,heterogeneous network embedding based recommendation becomes a very hot research topic in recent years.However,most of the existing studies do not fully explore the auxiliary information and complex relations which are valuable for enhancing recommending performance.To address the above problems,a recommendation algorithm based on heterogeneous information network embedding and attention neural network is proposed.First,this paper proposes a heterogeneous information network embedding method that maintains semantic relationship and topological structure simultaneously.Then,it designs a meta-path based random walk strategy to extract node sequences from heterogeneous information networks.All the sequences are filtered and then employed to learn the embeddings for each user and item in different meta-paths.At last,this paper presents a recommendation algorithm based on attention neural network with the above embeddings as input.The attention network composed of attention layers and hidden layers is able to explore the complex relationships and hence enhance the performance of recommendation.To verify the effectiveness of the proposed method,this paper conducts experiments on two kinds of real-world datasets and makes a comparison with three competitive algorithms.The results show that the proposed algorithm improves the recommending performance in terms of MAE and RMSE,with a maximum increase of 8.9%.

Key words: Heterogeneous information networks, Representation learning, Meta-path, Attention neural network, Recommendation algorithm

中图分类号: 

  • TP181
[1]SARWAR B,KARYPIS G,KONSTAN J,et al.Analysis of re-commendation algorithms for e-commerce[C]//Proceedings of the 2nd ACM Conference on Electronic Commerce.Association for Computing Machinery.2000:158-167.
[2]SCHAFER J B,KONSTAN J A,RIEDL J.E-commerce recommendation applications[J].Data Mining and Knowledge Disco-very,2001,5(1/2):115-153.
[3]YE M,YIN P,LEE W C.Location recommendation for location-based social networks[C]//Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems.Association for Computing Machinery,2010:458-461.
[4]SONG Y,ZHANG L,GILES C L.Automatic tag recommendation algorithms for social recommender systems[J].ACM Transactions on the Web,2011,5(1):1-31.
[5]DAVIDSON J,LIEBALD B,LIU J,et al.The YouTube video recommendation system[C]//Proceedings of the fourth ACM Conference on Recommender Systems.Association for Computing Machinery,2010:293-296.
[6]ZHOU C H,SHEN J J,LI Y,et al.Review of classical recommendation algorithms[J].Computer Science and Application,2019,9(9):1803-1817.
[7]PAZZANI M J,BILLSUS D.Content-based recommendationsystems[M].The Adaptive Web.Berlin:Springer,2007:325-341.
[8]LINDEN G,SMITH B,YORK J.Amazon.com recommenda-tions:Item-to-item collaborative filtering[J].IEEE Internet Computing,2003,7(1):76-80.
[9]CHOI K,YOO D,KIM G,et al.A hybrid online-product recommendation system:Combining implicit rating-based collaborative filtering and sequential pattern analysis[J].Electronic Commerce Research and Applications,2012,11(4):309-317.
[10]HAO R F,ZHANG G M,CHENG Y Q.Socialized Matrix Factorization Recommendation Algorithm with User RatingPrefe-rence Confidence[J].Journal of Chongqing University of Technology (Natural Science),2020,34(11):138-146.
[11]PAZZANI M J.A framework for collaborative,content-basedand demographic filtering[J].Artificial Intelligence Review,1999,13(5/6):393-408.
[12]LUO H,NIU C,SHEN R,et al.A collaborative filtering framework based on both local user similarity and global user similarity[J].Machine Learning,2008,72(3):231-245.
[13]SARWAR B,KARYPIS G,KONSTAN J,et al.Item-based collaborative filtering recommendation algorithms[C]//Procee-dings of the 10th international conference on World Wide Web.Association for Computing Machinery,2001:285-295.
[14]SHI C,LI Y,ZHANG J,et al.A survey of heterogeneous information network analysis[J].IEEE Transactions on Knowledge and Data Engineering,2016,29(1):17-37.
[15]SHI C,ZHOU C,KONG X,et al.Heterecom:a semantic-based recommendation system in heterogeneous networks[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Association for Computing Machinery,2012:1552-1555.
[16]JAMALI M,LAKSHMANAN L.HeteroMF:recommendation in heterogeneous information networks using context dependent factor models[C]//Proceedings of the 22nd International Conference on World Wide Web.Association for Computing Machinery,2013:643-654.
[17]YAN B,ZHANG L,GUO L,et al.Personalized Recommendation Based on Tag Semantics in the Heterogeneous Information Network[C]//China Conference on Wireless Sensor Networks.Springer,2019:224-235.
[18]LUO C,PANG W,WANG Z,et al.Hete-CF:Social-based collaborative filtering recommendation using heterogeneous relations[C]//2014 IEEE International Conference on Data Mi-ning.IEEE,2014:917-922.
[19]NIU Y Q,MENG Y Y,NIU Q F.Text Recommendation Based on Heterogeneous Attention Recurrent Neural Network[J].Computer Engineering,2020,46(10):52-59.
[20]CAO B,LIU N N,YANG Q.Transfer learning for collective link prediction in multiple heterogenous domains[C]//Procee-dings of the 27th International Conference on Machine Lear-ning.Omnipress,2010:159-166.
[21]JACOB Y,DENOYER L,GALLINARI P.Learning latent representations of nodes for classifying in heterogeneous social networks[C]//Proceedings of the 7th ACM International Confe-rence on Web Search and Data Mining.Association for Computing Machinery,2014:373-382.
[22]TANG J,QU M,MEI Q.Pte:Predictive text embeddingthrough large-scale heterogeneous text networks[C]//Procee-dings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Association for Computing Machinery,2015:1165-1174.
[23]TANG J,QU M,WANG M,et al.Line:Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.International World Wide Web Conferences Steering Committee,2015:1067-1077.
[24]SUN Y,HAN J.Mining heterogeneous information networks:principles and methodologies[J].Synthesis Lectures on Data Mining and Knowledge Discovery,2012,3(2):1-159.
[25]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.
[26]CHEN Y,WANG C.HINE:Heterogeneous information net-work embedding[C]//Proceedings of the International Confe-rence on Database Systems for Advanced Applications.Sprin-ger,2017:180-195.
[27]DONG Y,CHAWLA N V,SWAMI A.metapath2vec:Scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Association for Computing Machinery,2017:135-144.
[28]PEROZZI B,AL-RFOU R,SKIENA S.Deepwalk:Online lear-ning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.Association for Computing Machinery,2014:701-710.
[29]GUTHRIE D,ALLISON B,LIU W,et al.A closer look at skip-gram modelling[C]//Proceedings of the 5th International Conference on Language Resources and Evaluation,2006:1222-1225.
[30]CHANG S,HAN W,TANG J,et al.Heterogeneous networkembedding via deep architectures[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.Association for Computing Machine-ry,2015:119-128.
[31]FU T,LEE W C,LEI Z.Hin2vec:Explore meta-paths in heterogeneous information networks for representation learning[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.Association for Computing Machine-ry,2017:1797-1806.
[32]YU X,REN X,SUN Y,et al.Recommendation in heterogeneous information networks with implicit user feedback[C]//Procee-dings of the 7th ACM Conference on Recommender Systems.Association for Computing Machinery,2013:347-350.
[33]HU B,SHI C,ZHAO W X,et al.Local and global information fusion for top-n recommendation in heterogeneous information network[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.Association for Computing Machinery,2018:1683-1686.
[34]SHI C,ZHANG Z,JI Y,et al.SemRec:a personalized semantic recommendation method based on weighted heterogeneous information networks[J].World Wide Web,2019,22(1):153-184.
[35]ZHAO H,YAO Q,LI J,et al.Meta-graph based recommendation fusion over heterogeneous information networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Association for Computing Machinery,2017:635-644.
[36]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.
[37]GROVER A,LESKOVEC J.Node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.Association for Computing Machinery,2016:855-864.
[38]BOTTOU L.Large-scale machine learning with stochastic gra-dient descent[C]//Proceedings of COMPSTAT'2010.2010:177-186.
[39]WILLMOTT C J,MATSUURA K.Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J].Climate Research,2005,30(1):79-82.
[40]MNIH A,SALAKHUTDINOV R R.Probabilistic matrix fac-torization[C]//Proceedings of the Twenty-First Annual Confe-rence on Neural Information Processing Systems.Curran Asso-ciates,2007:1257-1264.
[41]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.2009:452-461.
[42]HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.International World Wide Web Conferences Steering Committee,2017:173-182.
[1] 杨如涵, 戴毅茹, 王坚, 董津. 基于表示学习的工业领域人机物本体融合[J]. 计算机科学, 2021, 48(5): 190-196.
[2] 熊旭东, 杜圣东, 夏琬钧, 李天瑞. 基于二分图卷积表示的推荐算法[J]. 计算机科学, 2021, 48(4): 78-84.
[3] 钱胜胜, 张天柱, 徐常胜. 多媒体社会事件分析综述[J]. 计算机科学, 2021, 48(3): 97-112.
[4] 李鑫超, 李培峰, 朱巧明. 一种基于层级信息优化的有向网络表示学习方法[J]. 计算机科学, 2021, 48(2): 100-104.
[5] 王雪岑, 张昱, 刘迎婕, 于戈. 基于表示学习的在线学习交互质量评价方法[J]. 计算机科学, 2021, 48(2): 207-211.
[6] 王瑞平, 贾真, 刘畅, 陈泽威, 李天瑞. 基于DeepFM的深度兴趣因子分解机网络[J]. 计算机科学, 2021, 48(1): 226-232.
[7] 丁钰, 魏浩, 潘志松, 刘鑫. 网络表示学习算法综述[J]. 计算机科学, 2020, 47(9): 52-59.
[8] 刘君良, 李晓光. 个性化推荐系统技术进展[J]. 计算机科学, 2020, 47(7): 47-55.
[9] 蒋宗礼, 李苗苗, 张津丽. 基于融合元路径图卷积的异质网络表示学习[J]. 计算机科学, 2020, 47(7): 231-235.
[10] 黄易, 申国伟, 赵文波, 郭春. 一种基于漏洞威胁模式的网络表示学习算法[J]. 计算机科学, 2020, 47(7): 292-298.
[11] 马海江. 基于卷积神经网络与约束概率矩阵分解的推荐算法[J]. 计算机科学, 2020, 47(6A): 540-545.
[12] 张志扬, 张凤荔, 陈学勤, 王瑞锦. 基于分层注意力的信息级联预测模型[J]. 计算机科学, 2020, 47(6): 201-209.
[13] 李鑫超, 李培峰, 朱巧明. 一种基于改进向量投影距离的知识图谱表示方法[J]. 计算机科学, 2020, 47(4): 189-193.
[14] 张虎, 周晶晶, 高海慧, 王鑫. 融合节点结构和内容的网络表示学习方法[J]. 计算机科学, 2020, 47(12): 119-124.
[15] 周波. 融合语义模型的二分网络推荐算法[J]. 计算机科学, 2020, 47(11A): 482-485.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[2] 侯彦娥,孔云峰,党兰学. 求解多车型校车路径问题的混合集合划分的GRASP算法[J]. 计算机科学, 2018, 45(4): 240 -246 .
[3] 徐周波,张鵾,宁黎华,古天龙. 图编辑距离概述[J]. 计算机科学, 2018, 45(4): 11 -18 .
[4] 张昱, 高克宁, 于戈. 一种融合节点属性信息的社会网络链接预测方法[J]. 计算机科学, 2018, 45(6): 41 -45 .
[5] 王国豪,李庆华,刘安丰. 多目标最优化云工作流调度进化遗传算法[J]. 计算机科学, 2018, 45(5): 31 -37 .
[6] 王劲松,蔡朝晖,李永凯,刘树波. 基于用户评分差异性和相关性的协同过滤推荐算法[J]. 计算机科学, 2018, 45(5): 190 -195 .
[7] 陈圣灵,沈思淇,李东升. 基于样本权重更新的不平衡数据集成学习方法[J]. 计算机科学, 2018, 45(7): 31 -37 .
[8] 高思齐,邢玉轩,肖侬,刘芳. 求解01背包问题的贪婪蛙跳算法[J]. 计算机科学, 2018, 45(7): 73 -77 .
[9] 甘玲, 赵福超, 杨梦. 一种自适应组稀疏表示的图像修复方法[J]. 计算机科学, 2018, 45(8): 272 -276 .
[10] 王慧玲, 綦小龙, 武港山. 基于深度卷积神经网络的目标检测技术的研究进展[J]. 计算机科学, 2018, 45(9): 11 -19 .