计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 129-138.doi: 10.11896/jsjkx.220300004

• 数据库&大数据&数据科学 • 上一篇    下一篇

异构信息网络的注意力感知多通道图卷积评分预测模型

周明强, 代开浪, 吴全旺, 朱庆生   

  1. 重庆大学计算机学院 重庆 400044
  • 收稿日期:2022-03-01 修回日期:2022-09-27 出版日期:2023-03-15 发布日期:2023-03-15
  • 通讯作者: 周明强(zmqmail@cqu.edu.cn)
  • 基金资助:
    国家自然科学基金(61702060);重庆市自然科学基金(cstc2020jcyj-msxmX0137)

Attention-aware Multi-channel Graph Convolutional Rating Prediction Model for Heterogeneous Information Networks

ZHOU Mingqiang, DAI Kailang, WU Quanwang, ZHU Qingsheng   

  1. College of Computer Science,Chongqing University,Chongqing 400044,China
  • Received:2022-03-01 Revised:2022-09-27 Online:2023-03-15 Published:2023-03-15
  • About author:ZHOU Mingqiang,born in 1977,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include the different aspects of software engineering,service computing,complex network and graph network representation learning and applications.
  • Supported by:
    National Natural Science Foundation of China(61702060) and Natural Science Foundation of Chongqing(cstc2020jcyj-msxmX0137).

摘要: 异构信息网络(Heterogeneous Information Network,HIN)包含了丰富的语义信息,利用其进行评分预测已成为缓解推荐系统数据稀疏性问题的一个重要途径。然而,传统采用元路径来提取HIN语义信息的方法忽略了元路径中的评分信息,从而导致元路径无法精确捕获用户和推荐项目之间的语义相似性,同时也未能良好区分不同元路径的重要性。为了解决这两个问题,首先提出了一种带有评分限制的元路径以获取更准确的HIN语义信息,利用这些信息构建用户和项目多层网络;然后结合图卷积网络和注意力机制设计了一个用于评分预测的神经网络,通过多通道图卷积有效地表示了HIN的多种语义信息,采用注意力机制区分不同元路径的重要性,弥补了传统方法的不足;最后融合了用户和项目的属性信息,进一步提高了评分预测的准确性。在Douban Book和Yelp数据集上的实验结果表明所提模型明显优于对比的基线模型,尤其在数据稀疏的情况下,均方根误差比基线模型最多减少了50%,从而验证了所提模型的优越性。

关键词: 评分预测, 元路径, 异构信息网络, 注意力机制, 图卷积网络

Abstract: Heterogeneous information network(HIN) contains rich semantic information,and the use of HIN for rating prediction has become an important way to alleviate the problem of data sparsity in recommender systems.However,the traditional methods using meta-paths to extract HIN semantic information ignore the rating information on the edges,making the meta-paths unable to accurately capture the semantic similarity between users and recommended items.And these methods also fail to distinguish the importance of different meta-paths.To address the two problems,rating constrained meta-path is proposed to obtain more accurate HIN semantic information which is then used to construct multi-layer homogeneous networks for users and items.Then,a neural network for rating prediction is designed by combining graph convolutional network and attention mechanism,which effectively represents various semantic information in HIN through multi-channel graph convolutional networks and distinguishes the importance of different meta-paths by using an attentional fusion function.Furthermore,the proposed model also integrates the attribute information of users and items to improve the accuracy of rating prediction.Experimental results on Douban Book and Yelp datasets show that the proposed model is significantly better than the comparative baseline models,especially in the case of sparse data,and the root mean square error reduces by up to 50% compared to the baseline model,thus verifying the superiority of the proposed model.

Key words: Rating prediction, Meta-path, Heterogeneous information network, Attention mechanism, Graph convolutional network

中图分类号: 

  • TP183
[1]WU J X,ZHANG Z H.Collaborative Filtering Recommendation Algorithm Based on User Rating and Similarity of Explicit and Implicit Interest [J].Computer Science,2021,48(5):147-154.
[2]HE Y F,ZHANG Y W,LV Z H,et al.Meta Path-Aware RatingCollaborative Filtering in Heterogeneous Information Network [J].Chinese Journal of Computers,2020,43(12):2385-2397.
[3]KOREN Y.Factor in the Neighbors:Scalable and Accurate Collaborative Filtering [J].ACM Transactions on Knowledge Discovery from Data,2010,4(1):1-24
[4]XU K,ZHENG X,CAI Y,et al.Improving User Recommendation by Extracting Social Topics and Interest Topics of Users in Uni-Directional Social Networks [J].Knowledge-Based Systems,2018,140(C):120-133.
[5]YANG N,MA Y,CHEN L,et al.A meta-feature based unified framework for both cold-start and warm-start explainable reco-mmendations [J].World Wide Web,2020,23(1):241-265.
[6]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.
[7]YIZHOU S,JIAWEI H.Mining Heterogeneous InformationNetworks:Principles and Methodologies [M].California:Morgan & Claypool,2012:57-72.
[8]YAN S,WANG H,LI Y,et al.Attention-aware metapath-based network embedding for HIN based recommendation [J].Expert Systems with Applications,2021,174(8):114601.1-114601.12.
[9]SHI C,HU B,ZHAO W X,et al.Heterogeneous InformationNetwork Embedding for Recommendation [J].IEEE Transactions on Knowledge & Data Engineering,2019,31(2):357-370.
[10]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.Halifax,NS,Canada:Association for Computing Machinery,2017:135-144.
[11]ZHAO J L,ZHAO Z Y.Recommendation Algorithm Based onHeterogeneous Information Network Embedding and Attention Neural Network [J].Computer Science,2021,48(8):72-79.
[12]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems [J].Computer,2009,42(8):30-37.
[13]FORSATI R,MAHDAVI M,SHAMSFARD M,et al.Matrix Factorization with Explicit Trust and Distrust Side Information for Improved Social Recommendation [J].ACM Transactions on Information Systems,2014,32(4):1-38.
[14]LIANG D,ALTOSAAR J,CHARLIN L,et al.FactorizationMeets the Item Embedding:Regularizing Matrix Factorization with Item Co-Occurrence[C]//Proceedings of the 10th ACM Conference on Recommender Systems.Association for Computing Machinery,2016:59-66.
[15]CAO D,NIE L,HE X,et al.Embedding Factorization Models for Jointly Recommending Items and User Generated Lists[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.Association for Computing Machinery,2017:585-594.
[16]LUO L,XIE H,RAO Y,et al.Personalized recommendation by matrix co-factorization with tags and time information [J].Expert Systems with Applications,2019,119(1):311-321.
[17]ZHANG Z,LIU Y,ZHANG Z,et al.Fused matrix factorization with multi-tag,social and geographical influences for POI re-commendation[J].World Wide Web,2019,22(3):1135-1150.
[18]NGUYEN V D,HUYNH V N,SRIBOONCHITTA S.Integrating Community Context Information Into a Reliably Weighted Collaborative Filtering System Using Soft Ratings [J].IEEE Transactions on Systems,Man,Cybernetics:Systems,2020,50(4):1318-1330.
[19]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.
[20]YU X,REN X,SUN Y,et al.Personalized Entity Recommendation:A Heterogeneous Information Network Approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.Association for Computing Machinery,2014:283-292.
[21]LIANG T,CHEN L,WU J,et al.Meta-Path Based Service Re-commendation in Heterogeneous Information Networks[C]//Service-Oriented Computing.Springer International Publishing,2016:371-386.
[22]DAI F,GU X,LI B,et al.Meta-Graph Based Attention-Aware Recommendation over Heterogeneous Information Networks[C]//Computational Science(ICCS 2019).Springer Interna-tional Publishing,2019:580-594.
[23]WU Z,PAN S,CHEN F,et al.A Comprehensive Survey onGraph Neural Networks [J].IEEE Transactions on Neural Networks and Learning Systems,2021,32(1):4-24.
[24]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.Long Beach,California,USA:Curran Associates Inc.,1025-1035.
[25]YING R,HE R,CHEN K,et al.Graph Convolutional Neural Networks for Web-Scale Recommender Systems[C]//Procee-dings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.London,United Kingdom:Association for Computing Machinery,2018:974-983.
[26]FU J,LIU J,JIANG J,et al.Scene Segmentation With Dual Relation-Aware Attention Network [J].IEEE Transactions onNeural Networks and Learning Systems,2021,32(6):2547-2560.
[27]SALAKHUTDINOV R,MNIH A.Probabilistic matrix factorization [C]//Proceedings of the 21st International Conference on Neural Information Processing Systems(NIPS’08),Curran Associates Inc.2008:1257-1264.
[1] 李帅, 徐彬, 韩祎珂, 廖同鑫.
SS-GCN:情感增强和句法增强的方面级情感分析模型
SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement
计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[2] 陈富强, 寇嘉敏, 苏利敏, 李克.
基于图神经网络的多信息优化实体对齐模型
Multi-information Optimized Entity Alignment Model Based on Graph Neural Network
计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[3] 陈姝睿, 梁子然, 饶洋辉.
细粒度语义知识图谱增强的中文OOV词嵌入学习
Fine-grained Semantic Knowledge Graph Enhanced Chinese OOV Word Embedding Learning
计算机科学, 2023, 50(3): 72-82. https://doi.org/10.11896/jsjkx.220700249
[4] 冯程程, 刘派, 姜琳颖, 梅笑寒, 郭贵冰.
文档增强型知识库问答
Document-enhanced Question Answering over Knowledge-Bases
计算机科学, 2023, 50(3): 266-275. https://doi.org/10.11896/jsjkx.220300022
[5] 邹芸竹, 杜圣东, 滕飞, 李天瑞.
一种基于多模态深度特征融合的视觉问答模型
Visual Question Answering Model Based on Multi-modal Deep Feature Fusion
计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303
[6] 王鹏宇, 台文鑫, 刘芳, 钟婷, 罗绪成, 周帆.
基于数据增强的自监督飞行航迹预测
Self-supervised Flight Trajectory Prediction Based on Data Augmentation
计算机科学, 2023, 50(2): 130-137. https://doi.org/10.11896/jsjkx.211200016
[7] 瞿中, 王彩云.
基于注意力机制和轻量级空洞卷积的混凝土路面裂缝检测
Crack Detection of Concrete Pavement Based on Attention Mechanism and Lightweight DilatedConvolution
计算机科学, 2023, 50(2): 231-236. https://doi.org/10.11896/jsjkx.211200290
[8] 刘露平, 周欣, 程军军, 何小海, 卿粼波, 王美玲.
基于会话式机器阅读理解模型的事件抽取方法
Event Extraction Method Based on Conversational Machine Reading Comprehension Model
计算机科学, 2023, 50(2): 275-284. https://doi.org/10.11896/jsjkx.220400271
[9] 蔡肖, 陈志华, 盛斌.
基于移位窗口金字塔Transformer的遥感图像目标检测
SPT:Swin Pyramid Transformer for Object Detection of Remote Sensing
计算机科学, 2023, 50(1): 105-113. https://doi.org/10.11896/jsjkx.211100208
[10] 张婧媛, 王宏霞, 何沛松.
基于Transformer的多任务图像拼接篡改检测算法
Multitask Transformer-based Network for Image Splicing Manipulation Detection
计算机科学, 2023, 50(1): 114-122. https://doi.org/10.11896/jsjkx.211100269
[11] 李雪辉, 张拥军, 史殿习, 徐化池, 史燕燕.
融合注意力特征的无锚框视觉目标跟踪方法
AFTM:Anchor-free Object Tracking Method with Attention Features
计算机科学, 2023, 50(1): 138-146. https://doi.org/10.11896/jsjkx.211000083
[12] 赵倩, 周冬明, 杨浩, 王长城.
残差注意力与多特征融合的图像去模糊
Image Deblurring Based on Residual Attention and Multi-feature Fusion
计算机科学, 2023, 50(1): 147-155. https://doi.org/10.11896/jsjkx.211100161
[13] 郑诚, 梅亮, 赵伊研, 张苏航.
基于双向注意力机制和门控图卷积网络的文本分类方法
Text Classification Method Based on Bidirectional Attention and Gated Graph Convolutional Networks
计算机科学, 2023, 50(1): 221-228. https://doi.org/10.11896/jsjkx.211100095
[14] 周芳泉, 成卫青.
基于全局增强图神经网络的序列推荐
Sequence Recommendation Based on Global Enhanced Graph Neural Network
计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[15] 黄丽, 朱焱, 李春平.
基于异构网络表征学习的作者学术行为预测
Author’s Academic Behavior Prediction Based on Heterogeneous Network Representation Learning
计算机科学, 2022, 49(9): 76-82. https://doi.org/10.11896/jsjkx.210900078
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!