计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221100030-8.doi: 10.11896/jsjkx.221100030

• 大数据&数据科学 • 上一篇    下一篇

基于课程学习和图嵌入的协同推荐

黄飞虎1,2, 帅剑波2, 彭舰2   

  1. 1 四川中电启明星信息技术有限公司 成都 610000
    2 四川大学计算机学院 成都 610065
  • 发布日期:2023-11-09
  • 通讯作者: 彭舰(penguest@scu.edu.cn)
  • 作者简介:(huangfh@scu.edu.cn)
  • 基金资助:
    四川省重点研发计划(22ZYFG0034);四川省重点实验室开放课题(SCITLAB-20001);四川大学博士后交叉学科基金(10822041A2137);四川大学宜宾市合作项目(2020CDYB-30)

Collaborative Recommendation Based on Curriculum Learning and Graph Embedding

HUANG Feihu1,2, SHUAI Jianbo2, PENG Jian2   

  1. 1 Aostar Information Technologies Co.,Ltd.,Chengdu 610000,China
    2 College of Computer Science,Sichuan University,Chengdu 610065,China
  • Published:2023-11-09
  • About author:HUANG Feihu,born in 1990,Ph.D,is a member of China Computer Federation.His main research interests include deep learning and data mining.
    PENG Jian,born in 1970,Ph.D,professor,Ph.D supervisor,is an outstanding member of China Computer Federation.His main research interests include big data and wireless sensor network.
  • Supported by:
    Sichuan Science and Technology Program(22ZYFG0034),Intelligent Terminal Key Laboratory of Sichuan Province(SCITLAB-20001),Post Doctoral Interdisciplinary Innovation Fund(10822041A2137) and Sichuan University and Yibin Cooperation Program(2020CDYB-30).

PDF (PC)

483

摘要： 推荐系统主要基于用户信息提供个性化服务。然而,用户对数据隐私泄露的广泛关注,给当前推荐算法提出了新的挑战。现有工作主要从差分隐私、匿名化、密码学和联邦学习的角度解决隐私泄露问题,但存在数据扰动和计算复杂的缺点。不同于现有工作,文中提出了基于课程学习和图神经网络的协同过滤模型(CLG-CF),充分利用评分表在隐式反馈的场景学习用户和物品嵌入。CLG-CF利用二部图建模评分表,基于图卷积网络实现用户和物品的表示学习,然后通过多层神经网络完成(用户,物品)对的预测。CLG-CF模型在训练过程中,采用负采样计算增强样本,为了解决样本的真伪问题,创新地引入课程学习指导模型学习。在3个真实的大规模数据集上进行了实验,结果表明 CLG-CF模型在不使用用户和物品信息的情况下,能够实现不错的推荐效果。

关键词: 推荐系统, 协同过滤, 课程学习, 图嵌入, 数据隐私

Abstract: Recommendation system mainly provide personalized services based on user information.However,users are widely concerned about data privacy issues,which poses new challenges to current recommendation algorithms.Existing works mainly address this problem based on the perspectives of differential privacy,anonymization,cryptography,and federated learning.Data disturbance and computational complexity are the main shortcomings of existing methods.Different from existing work,this paper proposes a collaborative filtering model based on curriculum learning and graph neural network(CLG-CF),which makes full use of rating information to learn the embedding of user and item in implicit feedback scenarios.CLG-CF utilizes a bipartite graph modeling scoring table,then realizes the representation learning of users and items based on graph convolutional networks,finally completes the prediction of(user,item) pairs through a multi-layer neural network.During the training process of the CLG-CF model,negative sampling is used to enhance training samples.In order to solve the problem of samples’ authenticity,the curriculum learning is innovatively introduced to guide the model learning.Extensive experiments are conducted on three real large-scale datasets,and the results show that the CLG-CF model can achieve good recommendation results without using user and item information.

Key words: Recommendation system, Collaborative filtering, Curriculum learning, Graph embedding, Data privacy

中图分类号: 

  • TP389
[1]REN S L,GUO H J,HUANG W H,et al.RecommendationMethod Based on Attention Mechanism InteractiveConvolu-tional Neural Network[J].Computer Science,2022,49(10):126-131.
[2]HUANG F,QIAO S,PENG J,et al.STPR:A Personalized Next Point-of-InterestRecommendation Model with Spatio-Temporal Effects Based on Purpose Ranking[J].IEEE Transactions on Emerging Topics in Computing,2021,9(2),994-1005.
[3]XU B,YI P Y,WANG J C,et al.High order Collaborative Filtering Recommendation System Based on Knowledge Graph Embedding[J].Computer Science,2021,48(S2):244-250.
[4]XU H,HUANG F,PENG J,et al.Intent-Aware Graph Neural Networks for Session-based Recommendation[C]//Interna-tional Joint Conference on Neural Networks(IJCNN).20221-8.
[5]TIAN L,HONG S.Research on legal regulation of the Big Data affinity[J].Cyber Security and Data Governance,2022,41(7):41-46.
[6]WANG L E,LI X C,LIU H Y.News recommendation method with knowledge graph and differential privacy[J].Journal of Computer Applications,2022,42(5):1339-1346.
[7]WEI R X,TIAN H,SHEN H.Improving k-anonymity basedprivacy preservation for collaborative filtering[J].Computers & Electrical Engineering,2018,67:509-519
[8]ZHANG H L,LI P D,WU J,et al.A Survey on Privacy-preserving Federated Recommender Systems[J].Acta Automatic Sini,2022,48(9):2142-2163.
[9]LIN G,LIANG F,PAN W,et al.Fedrec:Federated recommendation with explicit feedback[J].IEEE Intelligent Systems,2020,36(5):21-30
[10]LING Y,CUO O,CAI F,et al.User-based clustering with top-n recommendation on cold-start problem[C]//2013 Third International Conference on Intelligent System Design and Engineering Applications.IEEE,2013:1585-1589.
[11]ZHOU K,YANG S H,ZHA H.Functional matrix factorizations for cold-start recommendation[C]//Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval.2011:315-324.
[12]ZHANG Y,CALLAN J,MINKA T.Novelty and redundancydetection in adaptive filtering[C]//Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.2002:81-88.
[13]ROBERTSON S.Threshold setting and performance optimiza-tion in adaptive filtering[J].Information Retrieval,2002,5(2):239-256.
[14]ZHOU G,ZHU X,SONG C,et al.Deep interest network for click-through rate prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:1059-1068.
[15]ZHOU G,MOU N,FAN Y,et al.Deep interest evolution network for click-through rate prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:5941-5948.
[16]SALAKHUTDINOV R,MNIH A,HINTON G.Restricted Boltzmann machines for collaborative filtering[C]//Proceedings of the 24th International Conference on Machine Learning.2007:791-798.
[17]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.
[18]YING R,HE R,CHEN K,et al.Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:974-983.
[19]BERG R V D,KIPF T N,WELLING M.Graph convolutional matrix completion[J].arXiv:170602263,2017.
[20]ZHANG M,CHEN Y.Inductive matrix completion based ongraph neural networks[J].arXiv:190412058,2019.
[21]WANG X,HE X,WANG M,et al.Neural graph collaborativefiltering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[22]BENGIO Y,LOURADOUR J,COLLOBERT R,et al.Curriculum learning[C]//Proceedings of the 26th Annual International Conference on Machine Learning.2009:41-48.
[23]WANG W,FENG F,HE X,et al.Denoising implicit feedback for recommendation[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining.2021:373-381.
[24]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 discovery and data mining.2014:701-710.
[25]CAO J,LIN X,GUO S,et al.Bipartite graph embedding via mutual informationmaximization[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mi-ning.2021:635-643.
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