计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (3): 161-168.doi: 10.11896/jsjkx.240500015

• 数据库&大数据&数据科学 • 上一篇    下一篇

融合知识图谱的负采样方法

陆海洋1, 柳先辉2, 侯文龙1   

  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
  • 收稿日期:2024-05-06 修回日期:2024-08-20 出版日期:2025-03-15 发布日期:2025-03-07
  • 通讯作者: 柳先辉(xianhuiliu488@163.com)
  • 作者简介:(Ocean@tongji.edu.cn)
  • 基金资助:
    国家重点研发计划(2022YFB3305700)

Negative Sampling Method for Fusing Knowledge Graph

LU Haiyang1, LIU Xianhui2, HOU Wenlong1   

  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
  • Received:2024-05-06 Revised:2024-08-20 Online:2025-03-15 Published:2025-03-07
  • About author:LU Haiyang,born in 1999,postgra-duate.His main research interests include knowledge graph and recommender systems.
    LIU Xianhui,born in 1979,Ph.D,associate professor.His main research in-terests include machine learning,data mining and big data,and networked manufacturing.
  • Supported by:
    National Key Research and Development Program of China(2022YFB3305700).

PDF (PC)

190

摘要： 为了解决信息过载的问题,推荐系统被广泛研究。由于很难获取大量高质量的显式反馈数据,隐式反馈数据成为训练推荐系统的主流选择。从未标记的数据中采样负例,即负采样,对于训练基于隐式反馈的推荐模型非常重要。现有推荐系统的负采样方法往往只关注如何选择包含更多用户偏好信息的强负样例,却没有考虑强负样例的假阴性问题。为了降低采样得到的负样例的假阴性概率并提高其信息量,提出了一种融合知识图谱的负采样方法。首先,根据用户-项目知识图谱构建负样例候选集;然后,通过基于贝叶斯分类的方式从候选集中筛选假阴性概率最小的负样例;最后,基于Mixup策略引入正混合技术构建强负样例。为了验证所提出方法的有效性,在两个公开数据集上进行了实验。结果表明,与现有方法相比,所提方法表现更优。

关键词: 负采样, 知识图谱, 推荐系统, 正混合

Abstract: In order to solve the problem of information overload,recommender systems have been widely studied.Since it is difficult to obtain a large amount of high-quality explicit feedback data,implicit feedback data becomes the mainstream choice for training re-commender systems.Sampling negative instances from unlabeled data,i.e.negative sampling,is crucial for training recommendation models based on implicit feedback data.The previous negative sampling methods often focus on how to select hard negative instances that contain more user preference information,without considering the false negative problem.In order to reduce the false negative probability of negative instances obtained from sampling and make them more informative,a negative sampling method that integrates knowledge graph is proposed.Firstly,constructing a candidate instance set based on the user-item knowledge graph.Then,the negative instance with the lowest false negative probability is selected from the candidate set through a Bayesian classification approach.Finally,based on the Mixup strategy,positive mixing technology is introduced to construct the hard negative instance.To evaluate the effectiveness of the proposed method,validation was conducted on two public datasets.The results show that compared with previous methods,the method proposed in this paper performs better.

Key words: Negative sampling, Knowledge graph, Recommender system, Positive mixing

中图分类号: 

  • TP391
[1]GOLDBERG D,NICHOLS D,OKI B M,et al.Using collaborative filtering to weave an information tapestry[J].Communications of the ACM,1992,35(12):61-70.
[2]KABBUR S,NING X,KARYPIS G.Fism:factored item simila-rity models for top-n recommender systems[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2013:659-667.
[3]KOREN Y.Factorization meets the neighborhood:a multiface-ted collaborative filtering model[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.2008:426-434.
[4]HE X,DENG K,WANG X,et al.Lightgcn:Simplifying andpowering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:639-648.
[5]WANG X,HE X,WANG M,et al.Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[6]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.
[7]GUO X W,XIA H B,LIU Y.Hybrid Recommendation Model of Knowledge Graph and Graph Convolutional Network[J].Journal of Frontiers of Computer Science and Technology,2022,16(6):1343-1353.
[8]LAI R,CHEN L,ZHAO Y,et al.Disentangled negative sampling for collaborative filtering[C]//Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining.2023:96-104.
[9]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian personalized ranking from implicit feedback[J].arXiv:1205.2618,2012.
[10]LIU B,WANG B.Bayesian Negative Sampling for Recommendation[C]//2023 IEEE 39th International Conference on Data Engineering.2023:749-761.
[11]ZHANG H,CISSE M,DAUPHIN Y N,et al.mixup:Beyondempirical risk minimization[J].arXiv:1710.09412,2017.
[12]SUN Z,GUO Q,YANG J,et al.Research commentary on recommendations with side information:A survey and research directions[J].Electronic Commerce Research and Applications,2019,37:100879.
[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.2001:285-295.
[14]YOO H,CHUNG K.Deep learning-based evolutionary recommendation model for heterogeneous big data integration[J].Transactions on Internet and Information Systems,2020,14(9):3730-3744.
[15]RAO Z Y,ZHANG Y,LIU J T,et al.Recommendation methods and systems using knowledge graph[J].Acta Automatica Sinica,2021,47(9):2061-2077.
[16]SHI C,ZHANG Z,LUO P,et al.Semantic path based persona-lized recommendation on weighted heterogeneous information networks[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.2015:453-462.
[17]WANG H,ZHANG F,WANG J,et al.Ripplenet:Propagating user 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.
[18]MA H D,FANG Y Q.Dynamic Negative Sampling for Graph Convolution Network Based Collaborative Filtering Recommendation Model[J].Computer Science,2023,50(S2):489-495.
[19]DIAZ-AVILES E,DRUMOND L,SCHMIDT-THIEME L,et al.Real-time top-n recommendation in social streams[C]//Proceedings of the Sixth ACM Conference on Recommender Systems.2012:59-66.
[20]CUI P,LIU S,ZHU W.General knowledge embedded imagerepresentation learning[J].IEEE Transactions on Multimedia,2017,20(1):198-207.
[21]HE X,ZHANG H,KAN M Y,et al.Fast matrix factorization for online recommendation with implicit feedback[C]//Procee-dings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.2016:549-558.
[22]TOGASHI R,OTANI M,SATOH S.Alleviating cold-startproblems in recommendation through pseudo-labelling over knowledge graph[C]// Proceedings of the 14th ACM International Conference on Web Search and Data Mining.2021:931-939.
[23]RENDLE S,FREUDENTHALER C.Improving pairwise lear-ning for item recommendation from implicit feedback[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.2014:273-282.
[24]ZHANG W,CHEN T,WANG J,et al.Optimizing top-n collabo-rative filtering via dynamic negative item sampling[C]//Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval.2013:785-788.
[25]ZHAO T,MCAULEY J,KING I.Improving latent factor mo-dels via personalized feature projection for one class recommendation[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.2015:821-830.
[26]YU L,ZHOU G,ZHANG C,et al.RankMBPR:Rank-awaremutual bayesian personalized ranking for item recommendation[C]//Web-Age Information Management:17th International Conference.2016:244-256.
[27]ZHAO Y,GUO G B,JIANG L Y.Adversarial Sampling for Social Recommender[J].Journal of Cyber Security,2021,6(5):88-98.
[28]DING J,QUAN Y,YAO Q,et al.Simplify and robustify negative sampling for implicit collaborative filtering[J].Advances in Neural Information Processing Systems,2020,33:1094-1105.
[29]HUANG T,DONG Y,DING M,et al.Mixgcf:An improvedtraining method for graph neural network-based recommender systems[C]// Proceedings of the 27th ACM SIGKDD Confe-rence on Knowledge Discovery & Data Mining.2021:665-674.
[30]WANG J,YU L,ZHANG W,et al.Irgan:A minimax game for unifying generative and discriminative information retrieval models[C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.2017:515-524.
[31]PARK D H,CHANG Y.Adversarial sampling and training for semi-supervised information retrieval[C]//The World Wide Web Conference.2019:1443-1453.
[32]ZHAO Y H,LIU L,WANG H L,et al.Survey of Knowledge Graph Recommendation System Research[J].Journal of Frontiers of Computer Science and Technology,2023,17(4):771-791.
[33]ANAGNOSTOPOULOS A,KUMAR R,MAHDIAN M.Influence and correlation in social networks[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2008:7-15.
[34]KALANTIDIS Y,SARIYILDIZ M B,PION N,et al.Hard negative mixing for contrastive learning[J].Advances in Neural Information Processing Systems,2020,33:21798-21809.
[35]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
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