计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230100057-7.doi: 10.11896/jsjkx.230100057

• 大数据&数据科学 • 上一篇    下一篇

结合图注意力机制的知识图谱推荐算法

张小婉1, 邓秋军2, 柳先辉2   

  1. 1 同济大学电子与信息工程学院 上海 201804
    2 同济大学电子与信息工程学院CAD研究中心 上海 201804
  • 发布日期:2023-11-09
  • 通讯作者: 柳先辉(xianhui_l@163.com)
  • 作者简介:(zhangxiaowan@tongji.edu.cn)
  • 基金资助:
    国家重点研发计划(2022YFB3305700)

Knowledge Graph Recommendation Algorithm Combined with Graph Attention Mechanism

ZHANG Xiaowan1, DENG Qiujun2, LIU Xianhui2   

  1. 1 College of Electronic and Information Engineering,Tongji University,Shanghai 201804,China
    2 CAD Research Center,College of Electronic and Information Engineering,Tongji University,Shanghai 201804,China
  • Published:2023-11-09
  • About author:ZHANG Xiaowan,born in 1997,master candidate.Her main research interests include recommender systems and knowledge graph.
    LIU Xianhui,born in 1979,Ph.D,associate researcher,associate professor.His main research interests include machine learning,data mining and big data,networked manufacturing.
  • Supported by:
    National Key Research and Development Program of China(2022YFB3305700).

PDF (PC)

998

摘要： 由于传统推荐算法存在数据稀疏性和冷启动问题,并且将物品作为单独的个体,没有考虑到物品之间存在的关系。为了解决这些问题,考虑引入知识图谱这一辅助信息。但现有的基于路径以及基于嵌入的知识图谱推荐算法没有考虑不同实体对于用户的重要性不同,导致重要性更低的实体对推荐结果的影响反而更大。针对这类局限性,文中提出了一种结合图注意力机制的知识图谱推荐系统,该推荐系统首先使用图嵌入方法生成用户和项目的初始表示,然后在表示传播时采用注意力机制区分不同邻居实体的重要性,通过权值加和来生成用户和项目的向量表示,最后预测层生成用户和项目的最终表示,并根据最终表示预测用户和项目交互的概率。在两个公开数据集Amazon-book和Last-fm上与其他算法进行对比实验,实验结果表明,该模型在指标recall,ndcg,precision,HR上均有提高,证明其能有效提高推荐的准确度。

关键词: 推荐系统, 知识图谱, 注意力机制, 高阶连通性, 实体传播

Abstract: Due to the problems of data sparsity and cold start in traditional recommendation algorithms,and the item is regarded as a separate individual,the relationship between items is not considered.In order to solve these problems,recommender systems start to introduce auxiliary information.However,the existing path-based and embedding-based knowledge graph recommendation algorithms do not consider the importance of different entities to users,resulting in entities with lower importance having a greater impact on the recommendation results.Aiming at such limitations,this paper proposes a knowledge graph recommendation system combining graph attention mechanism,which firstly uses graph embedding method to generate initial representations of users and items,and then employs an attention mechanism to distinguish the importance of different neighbor entities during representation propagation,and generates user and item sums through weight summation.The final prediction layer generates the final representation of the user and item,and predicts the probability of user and item interaction based on the final representation.Compared with other algorithms on two public datasets Amazon-book and Last-fm,and experimental results show that the model has improved in indicators recall,ndcg,precision,HR,indicating that the model can effectively improve the accuracy of recommendation.

Key words: Recommendation system, Knowledge graph, Attention mechanism, Higher-order connectivity, Embedding propagation

中图分类号: 

  • TP391
[1]KHAN N,MA Z M,ULLAH A,et al.Categorization of know-ledge graph based recommendation methods and benchmark datasets from the perspectives of application scenarios:A comprehensive survey[J].Expert Systems with Applications,2022,206:117737.
[2]YU C L,WANG W Q,LIU X,et al.FolkScope:IntentionKnowledge Graph Construction for E-commerce Commonsense Discovery[J].arXiv:2211.08316,2023.
[3]BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:acollaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data.ACM,2008:1247-1250.
[4]LEHMANN J,ISELE R,JAKOB M,et al.Dbpedia-a large-scale,multilingual knowledge base extracted from wikipedia[J].Semantic Web,2015,6(2):167-195.
[5]SUCHANEK F M,KASNECI G,WEIKUM G.Yago:a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web.ACM,2007:697-706.
[6]CARLSO N,BETTERIDGE J,WANG R C,et al.Coupled semi-supervised learning for information extraction[C]//Proceedings of the Third ACM International Conference on Web Search and Data Mining.ACM,2010:101-110.
[7]BELLEAU F,NOLIN M A,TOURIGNY N,et al.Bio2rdf:towards a mashup to build bioinformatics knowledge systems[J].Journal of Biomedical Informatics,2008,41(5):706-716.
[8]ZHOU L,GAO J F,LI D.The Design and Implementation ofXiaoIce,an Empathetic Social Chatbot[J].Computational Linguistics,2020,46(1):53-93.
[9]GAUR M,GUNARATNA K,SRINIVASAN V,et al.ISEEQ:Information Seeking Question Generation Using Dynamic Meta-Information Retrieval and Knowledge Graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022,36(10):10672-10680.
[10]WU L,HE X,WANG X,et al.A Survey on Accuracy-Oriented Neural Recommendation:From Collaborative Filtering to Information-Rich Recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(5):4425-4445.
[11]WANG X,HE X N,CAO Y X,et al.KGAT:Knowledge graph attention network for recommendation[C]//Proc of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.ACM Press,2019:950-958.
[12]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[J].Advances in Neural Information Processing Systems,2017,30:5998-6008.
[13]TAN T Z,YAN J B.Hybrid recommendation system based on self- attention model[J].Computer Engineering and Applications,2020,56(13):172-180.
[14]ZHANG F Z,YUAN N J,LIAN D F,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM Press,2016:353-362.
[15]WANG H W,ZHANG F Z,XIE X,et al.DKN:Deep know-ledge-aware network for news recommendation[C]//The 27th International Conference on World Wide Web.ACM,2018:1835-1844.
[16]YU X,REN X,SUN Y Z,et al.Personalized entity recommendation:A heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.ACM,2014:283-292.
[17]ZHAO H,YAO Q M,LI J D,et al.Metagraph based recommen-dation fusion over heterogeneous information networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2017:635-644.
[18]WANG H W,ZHANG F Z,WANG J J,et al.Ripplenet:Propagating user preferences on the knowledge graph for recommender systems[C]//Proc of the 27th ACM International Conference on Information and Knowledge Management.ACM Press,2018:417-426.
[19]WANG H W,ZHAO M,XIE X,et al.Knowledge Graph Convolutional Networks for Recommender Systems[C]//The World Wide Web Conference.ACM Press,2019:3307-3313.
[20]LIU Y,YANG S,XU Y,et al.Contextualized Graph Attention Network for Recommendation With Item Knowledge Graph[J].IEEE Transactions on Knowledge and Data Engineering,2023,35(1):181-195.
[21]YUAN M,WAN J,WANG D.CRM-SBKG:Effective CitationRecommendation by Siamese BERT and Knowledge Graph[C]//International Conference on Electrical Engineering,Big Data and Algorithms(EEBDA).2023:909-914.
[22]LIN Y K,LIU Z Y,SUN M S,et al.Learning Entity and Relation Embeddings for Knowledge Graph Completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.AAAI,2015:2181-2187.
[23]XU K,LI C T,TIAN Y L,et al.Representation Learning onGraphs with Jumping Knowledge Networks[C]//International Conference on Machine Learning.ACM,2018:5449-5458.
[24]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian Personalized Ranking from Implicit Feedback[C]//International Conference on Uncertainty in Artificial Intelligence.AUAI,2009:452-461.
[25]KINGMA D P,JIMMY B A.Adam:A Method for Stochastic Optimization[J].International Conference on Learning Representations.arXiv:1412.6980,2014.
[26]HE R N,MCAULEY J.Ups and Downs:Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering[C]//International World Wide Web Conferences.ACM,2016:507-517.
[27]HE X N A,LIAO L Z,ZHANG H W,et al.Neural Collaborative Filtering[C]//The World Wide Web Conference.ACM Press,2017:173-182.
[28]YANG J H,CHEN C M,WANG C J,et al.HOP-rec:high-order proximity for implicit recommendation[C]//Proceedings of the 12th ACM Conference on Recommender Systems.ACM,2018:140-144.
[29]HE X N,CHUA T S.Neural Factorization Machines for SparsePredictive Analytics[C]//International Conference on Research on Development in Information Retrieval.ACM,2017:355-364.
[30]AI Q Y,AZIZI V,CHEN X,et al.Learning HeterogeneousKnowledge Base Embeddings for Explainable Recommendation[J].Algorithms,2018,11(9):137.
[31]BORDES A,USUNIER N,GARCÍA-DURÁN A,et al.Translating Embeddings for Modeling Multi-relational Data[C]//NeurIPS.MIT Press,2013:2787-2795.
[32]VAN DEN BERG R,KIPF T N,WELLIN G.Graph Convolutional Matrix Completion[J].arXiv:1706.02263,2017.
[33]THOMAS N K,MAX W L.Semi-Supervised Classification with Graph Convolutional Networks.In ICLR[J].arXiv:1609.02907,2016.
[34]XAVIER G,YOSHUA B.Understanding the difficulty of training deep feedforward neural networks[C]//Artificial Intelligence and Statistics.JMLR,2010:249-256.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发