计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (8): 313-323.doi: 10.11896/jsjkx.230500143

• 人工智能 • 上一篇    下一篇

基于知识图谱与邻域感知注意力机制的推荐算法研究

陈珊珊, 姚苏滨   

  1. 南京邮电大学计算机学院/软件学院/网络空间安全学院 南京 210003
  • 收稿日期:2023-05-22 修回日期:2024-03-04 出版日期:2024-08-15 发布日期:2024-08-13
  • 通讯作者: 陈珊珊(chenss@njupt.edu.cn)

Study on Recommendation Algorithms Based on Knowledge Graph and Neighbor PerceptionAttention Mechanism

CHEN Shanshan, YAO Subin   

  1. School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:2023-05-22 Revised:2024-03-04 Online:2024-08-15 Published:2024-08-13
  • About author:CHEN Shanshan,born in 1980,Ph.D,associate professor.Her main research interests include large-scale distributed storage systems and architectures and so on.
       

PDF (PC)

419

摘要： 为解决传统推荐算法在面对数据稀疏的推荐任务时产生的冷启动问题,本研究将知识图谱引入推荐算法,结合一种新的邻域感知注意力机制代替传统图注意力机制来挖掘实体间的高阶连通信息,提出了基于知识图谱和邻域感知注意力机制的推荐模型KGNPAN。得益于知识图谱可使推荐具有精准、多样和可解释的特点,该模型能够很好地缓解数据稀疏与冷启动问题。首先利用基于自对抗负采样的图嵌入方法RotatE对原有物品和用户表征的语义信息进行扩充,将实体和关系向量映射成低维嵌入向量;其次,根据协同邻居的不同类型分别应用邻域感知注意力机制聚合邻居节点信息,丰富目标节点语义,并以卷积形式递归挖掘高阶连通信息;最后对用户与项目向量应用内积操作计算交互概率,得到推荐结果。在Amazon-book和Last-FM两个公共基准数据集上进行实验,结果表明,在与CKE,BPRMF,RippleNet,KGAT,KGCN和CAKN 6个基准模型的对比中,KGNPAN相较于基准模型中结果最优的CAKN模型,在召回率(Recall)上分别提升了1.30%和1.37%,在归一化折损累计增益上(NDCG)分别提升了1.26%和1.14%,充分验证了其有效性和可解释性。

关键词: 推荐算法, 邻域感知注意力机制, 知识图谱, 图神经网络, 冷启动

Abstract: In order to solve the cold start problem caused by traditional recommendation algorithms when they face the recommendation task with sparse data,this paper introduces the knowledge graph into the recommendation algorithm,combing a new neighbor perception attention mechanism to replace the traditional graph attention mechanism to mine the higher-order connected information between entities,and proposes a recommendation model KGNPAN based on the knowledge graph and neighbor perce-ption attention mechanism.Thanks to the knowledge graph,recommendations can be accurate,diverse and interpretable.This model can effectively alleviate issues of data sparsity and cold start.Firstly,this model utilizes the graph embedding method RotatE based on self adversarial negative sampling to expand the semantic information of the original item and user representations,mapping entity and relationship vectors into low dimensional embedding vectors.Secondly,based on the different types of collaborative neighbors,neighbor perception attention mechanisms are applied to aggregate neighbor node information,enrich the semantics of target nodes,and recursively mine high-order connected information in convolutional form.Finally,the inner product operation is applied to calculate the interaction probability between the user and the project vector,and the recommendation result is obtained.Experiments are conducted on two common benchmark datasets,Amazon-book and Last-FM,and compared with six benchmark models,namely CKE,BPRMF,RippleNet,KGAT,KGCN,and CAKN,KGNPAN.The results show that KGNPAN improves the recall rate by 1.30% and 1.37%,and normalized discounted cumulative gain(NDCG) increases by 1.26% and 1.14%,respectively,compared with CAKN model,which has the best performance in the benchmark modes,verifying the effectiveness and interpretability of the model.

Key words: Recommended algorithm, Neighbor perception attention mechanism, Knowledge graph, Graph neural network, Cold start

中图分类号: 

  • TP181
[1]CHENG Y H,LIU N,LU Y,et al.Recurrent knowledge attention network for movie recommendation[C]//2020 3rd International Conference on Electron Device and Mechanical Enginee-ring(ICEDME).IEEE,2020:648-651.
[2]MA W,ZHANG M,CAO Y,et al.Jointly learning explainable rules for recommendation with knowledge graph[C]//The World Wide Web Conference.2019:1210-1221.
[3]LIU D Y,LIAN J X,WANG S Y,et al.KRED:Knowledge-aware document representation for news recommendations[C]//Proceedings of the 14th ACM Conference on Recommender Systems.2020:200-209.
[4]HANSEN C,HANSEN C,MAYSTRE L,et al.Contextual and sequential user embeddings for large-scale music recommendation[C]//Proceedings of the 14th ACM Conference on Recommender Systems.2020:53-62.
[5]SHU J B,SHEN X X,LIU H,et al.A content-based recommendation algorithm for learning resources[J].Multimedia Systems,2018,24(2):163-173.
[6]NILASHI M,OTHMAN BIN I,NORAFIDA I.Multi-criteriacollaborative filtering with high accuracy using higherorder singular value decomposition and Neuro-Fuzzysystem[J].Know-ledge-Based Systems,2014,60:82-101.
[7]ZHANG J D,CHOW C Y,XU J.Enabling kernel-based attri-bute-aware matrix factorization for rating prediction[J].IEEE Transactions on Knowledge and Data Engineering,2016,29(4):798-812.
[8]LU Q B,GUO F P.Personalized information recommendationmodel based on context contribution and item correlation[J].Measurement,2019,142:30-39.
[9]YE J M,SONG J Q,ZHANG K,et al.Research on ExerciseRecommendation Algorithm for Online Judge System Enhanced by Knowledge Graph[J].Journal of Chinese Computer Systems,2023,44(11):2558-2565.
[10]ZHAGN X X,TANG Y Q,ZHAO W,et al.Personalized Lear-ning Resource Recommendation Based on Knowledge Graph and Graph Embedding[J].Computer Systems & Applications,2023,32(5):180-187.
[11]LUO C T,YE X.Survey on Knowledge Graph-Based Recom-mendation Methods[J].Computer Engineering and Applications,2023,59(1):49-60.
[12]WANG H,ZHANG F,XIE X,et al.DKN:Deep knowledge-aware network for news recommendation[C]//Proceedings of the 2018 World Wide Web Conference.2018:1835-1844.
[13]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958.
[14]VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graphattention networks[J].arXiv:1710.10903,2017.
[15]ZHAO H,YAO Q,LI J, et al.Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks[J].SIGKDD Explorations,2017(CD/ROM):584-593.
[16]XIAN Y,FU Z,MUTHUKRISHNAN S,et al.Reinforcementknowledge graph reasoning for explainable recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:285-294.
[17]HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:1025-1035.
[18]ZHANG F,YUAN N J,LIAN D,et al.Collaborative know-ledge base embedding for recommender systems[C]//Procee-dings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:353-362.
[19]JI G,HE S,XU L,et al.Knowledge graph embedding via dy-namic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(volume 1:Long papers).2015:687-696.
[20]WANG H,ZHANG F,WANG J,et al.Ripplenet:Propagatinguser preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM International Confe-rence on Information and Knowledge Management.2018:417-426.
[21]LIN X,QUAN Z,WANG Z J,et al.KGNN:Knowledge Graph Neural Network for Drug-Drug Interaction Prediction[C]//IJCAI.2020:2739-2745.
[22]WANG H,ZHAO M,XIE X,et al.Knowledge graph convolutional networks for recommender systems[C]//The World Wide Web Conference.2019:3307-3313.
[23]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems－Volume 2.2787-2795.
[24]WANG Z,ZHANG J,FENG J,et al.Knowledgegraph embed-ding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014,28(1).
[25]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.2015.
[26]SUN Z,DENG Z H,NIE J Y,et al.Rotate:Knowledge graph embedding by relational rotation in complex space[J].arXiv:1902.10197,2019.
[27]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//ICML.2011.
[28]YANG B,YIH S W,HE X,et al.Embedding Entities and Relations for Learning and Inference in Knowledge Bases[C]//Proceedings of the International Conference on Learning Representations(ICLR).2015.
[29]HAMILTON W,YING Z T,LESKOVEC J.Inductiverepresen-tation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:1025-1035.
[30]ZHANG F Z,YUAN N J,LIAN D F,et al.Collaborative know-ledge base embedding for recommender systems[C]//Procee-dings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016.
[31]RENDLE S,FREUENTHALER C,GANTNER Z,et al.BPR:Bayesian personalized ranking from implicit feedback[C]//Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence.2012:452-461.
[32]WANG H,ZHAO M,XIE X,et al.Knowledge graph convolutional networks for recommender systems[C]//The World Wide Web Conference.2019:3307-3313.
[33]WANG Z,LIN G,TAN H,et al.CKAN:collaborative know-ledge-aware attentive network for recommender systems[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:219-228.
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