融合纳什均衡策略和神经协同过滤的群组推荐方法

doi:10.16451/j.cnki.issn1003-6059.202205003

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (808 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要群组推荐中的核心问题是群组成员的偏好融合.传统的融合策略大多属于单一型策略,在一定程度上无法更好地满足群组的整体偏好需求.为此,文中提出融合纳什均衡策略和神经协同过滤的群组推荐方法.首先,通过多层感知机获得用户与项目之间潜在特征向量的非线性交互,并联合潜在因子模型和多层感知机实现用户与项目之间的协同过滤推荐.然后,基于个体的推荐评分设计基于纳什均衡的融合策略,更好地保证群组成员的平均满意度达到最大化.最后,在KDD CUP 数据集上的实验表明,文中方法在推荐模型和融合策略方面都具有较优的推荐性能.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李琳
	王培培
	杜佳
	周栋

关键词 ：协同过滤, 纳什均衡, 神经网络, 群组推荐

Abstract：The preference fusion of group members is the central problem of group recommendation. Most of the traditional fusion strategies are single type strategy, and they cannot meet the overall preference needs of the group to some extent. Therefore, a group recommendation method with Nash equilibrium strategy and neural collaborative filtering is proposed. The nonlinear interaction of potential feature vectors between users and items is obtained through multi-layer perceptron, and then the latent factor model and multi-layer perceptron are combined to realize collaborative filtering recommendation between users and items. Furthermore, a fusion strategy based on Nash equilibrium is designed based on individual recommendation scores to ensure maximum average satisfaction of group members. Experimental results on KDD CUP dataset show that the proposed method generates better recommendation performance than the benchmark method in terms of recommendation model and fusion strategy.

Key words： Collaborative Filtering Nash Equilibrium Neural Networks Group Recommendation

收稿日期: 2022-02-28

ZTFLH:

TP391

基金资助:国家自然科学基金青年项目(No.62106070)、湖北省重点研发计划项目(No.2021BAA030)资助

通讯作者: 李琳,博士,教授,主要研究方向为信息检索、推荐系统、机器学习、数据挖掘.E-mail:cathylilin@whut.edu.cn.

作者简介: 王培培,博士研究生,主要研究方向为自然语言处理、推荐系统.E-mail:ppwang07@whut.edu.cn.
杜佳,硕士研究生,主要研究方向为数据挖掘、组推荐、信息检索.E-mail:1119251283@qq.com.
周栋,博士,教授,主要研究方向为数据挖掘、信息检索、推荐系统.E-mail:dongzhou1979@hotmail.com.

引用本文:

李琳, 王培培, 杜佳, 周栋. 融合纳什均衡策略和神经协同过滤的群组推荐方法[J]. 模式识别与人工智能, 2022, 35(5): 412-421. LI Lin, WANG Peipei, DU Jia, ZHOU Dong. Group Recommendation Method with Nash Equilibrium Strategy and Neural Collaborative Filtering. Pattern Recognition and Artificial Intelligence, 2022, 35(5): 412-421.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202205003 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I5/412

[1] ZHANG S, YAO L N, SUN A X, et al. Deep Learning Based Re-commender System: A Survey and New Perspectives. ACM Computing Surveys, 2020, 52(1). DOI: 10.1145/3285029.
[2] FELFERNIG A, BORATTO L, STETTINGER M, et al. Group Re-commender Systems: An Introduction. Berlin, Germany: Springer, 2018.
[3] CAO D, HE X N, MIAO L H, et al. Social-Enhanced Attentive Group Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(3): 1195-1209.
[4] BALTRUNAS L, MAKCINSKAS T, RICCI F. Group Recommendations with Rank Aggregation and Collaborative Filtering // Proc of the 4th ACM Conference on Recommender Systems. New York, USA: ACM, 2010: 119-126.
[5] DARA S, CHOWDARY C R, KUMAR C. A Survey on Group Re-commender Systems. Journal of Intelligent Information Systems, 2020, 54(2): 271-295.
[6] ZOU L X, XIA L, GU Y L, et al. Neural Interactive Collaborative Filtering // Proc of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2020: 749-758.
[7] LIAN D F, ZHENG K, GE Y, et al. GeoMF++: Scalable Location Recommendation via Joint Geographical Modeling and Matrix Factori-zation. ACM Transactions on Information Systems, 2018, 36(3). DOI: 10.1145/3182166.
[8] 谢雨洋,冯栩,喻文健,等.基于随机化矩阵分解的网络嵌入方法.计算机学报, 2021, 44(3): 447-461.
(XIE Y Y, FENG X, YU W J, et al. Learning Network Embedding with Randomized Matrix Factorization. Chinese Journal of Compu-ters, 2021, 44(3): 447-461.)
[9] KUMAR R, VERMA B K, RASTOGI S S. Social Popularity Based SVD++ Recommender System. International Journal of Computer Applications, 2014, 87(14): 33-37.
[10] KOREN Y, BELL R, VOLINSKY C. Matrix Factorization Techniques for Recommender Systems. Computer, 2009, 42(8): 30-37.
[11] LIU Y, WANG S, KHAN M S, et al. A Novel Deep Hybrid Re-commender System Based on Auto-Encoder with Neural Collaborative Filtering. Big Data Mining and Analytics, 2018, 1(3): 211-221.
[12] JALALI S, HOSSEINI M. Collaborative Filtering in Dynamic Networks Based on Deep Auto-Encoder. The Journal of Supercompu-ting, 2022, 78(5): 7410-7427.
[13] WU D Q, LUO X, MA Z Y, et al. Composition-Enhanced Graph Collaborative Filtering for Multi-behavior Recommendation // Proc of the IEEE International Conference on Data Mining. Washington, USA: IEEE, 2021: 1427-1432.
[14] SUN J N, CHENG Z Y, ZUBERI S, et al. HGCF: Hyperbolic Graph Convolution Networks for Collaborative Filtering // Proc of the Web Conference. New York, USA: ACM, 2021: 593-601.
[15] HE X N, LIAO L Z, ZHANG H W, et al. Neural Collaborative Filtering // Proc of the 26th International Conference on World Wide Web. New York, USA: ACM, 2017: 173-182.
[16] XUE F, HE X N, WANG X, et al. Deep Item-Based Collaborative Filtering for Top-N Recommendation. ACM Transactions on Information Systems, 2019, 37(3). DOI: 10.1145/3314578.
[17] QUIJANO-SANCHEZ L, RECIO-GARCIA J A, DIAZ-AGUDO B, et al. Social Factors in Group Recommender Systems. ACM Tran-sactions on Intelligent Systems and Technology, 2013, 4(1). DOI: 10.1145/2414425.2414433.
[18] WANG Z J, YU N N, WANG J X. Collaborative Filtering Reco-mmendation Algorithm Based on Matrix Factorization and User Nearest Neighbors // Proc of the 16th Asia Simulation Conference and SCS Autumn Simulation Multi-conference. Berlin, Germany: Springer, 2016: 199-207.
[19] ZENG X L, WU B, SHI J, et al. Parallelization of Latent Group Model for Group Recommendation Algorithm // Proc of the 1st IEEE International Conference on Data Science in Cyberspace. Washington, USA: IEEE, 2016: 80-89.
[20] 曾雪琳. 基于群组关系的推荐算法研究与应用.硕士学位论文.北京: 北京邮电大学, 2017.
(ZENG X L. The Research and Application of Recommendation Based on Group Relationship. Master Dissertation. Beijing, China: Beijing University of Posts and Telecommunications, 2017.)
[21] ZHAO H K, LIU Q, GE Y, et al. Group Preference Aggregation: A Nash Equilibrium Approach // Proc of the 16th IEEE International Conference on Data Mining. Washington, USA: IEEE, 2016: 679-688.
[22] SEO Y D, KIM Y G, LEE E, et al. An Enhanced Aggregation Method Considering Deviations for a Group Recommendation. Expert Systems with Applications, 2018, 93: 299-312.
[23] BORATTO L, CARTA S, FENU G. Discovery and Representation of the Preferences of Automatically Detected Groups: Exploiting the Link between Group Modeling and Clustering. Future Generation Computer Systems, 2016, 64: 165-174.
[24] YALCIN E, ISMAILOGLU F, BILGE A. An Entropy Empowered Hybridized Aggregation Technique for Group Recommender Systems. Expert Systems with Applications, 2021, 166. DOI: 10.1016/j.eswa.2020.114111.
[25] CARVALHO L A M C, MACEDO H T. Users' Satisfaction in Re-commendation Systems for Groups: An Approach Based on Nonco-operative Games // Proc of the 22nd International Conference on World Wide Web. New York, USA: ACM, 2013: 951-958.
[26] HUANG Z H, XU X, ZHU H H, et al. An Efficient Group Re-commendation Model with Multiattention-Based Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(11): 4461-4474.
[27] 谷鹏,李琳,苏畅,等.面向群组的社交follow推荐方法研究.小型微型计算机系统, 2017, 38(5): 946-950.
(GU P, LI L, SU C, et al. Group Recommendation Approach for Social Follow Relationship. Journal of Chinese Computer Systems, 2017, 38(5): 946-950.)
[28] 王晨一. 基于纳什均衡的群组划分和推荐研究.硕士学位论文.南京:南京邮电大学, 2020.
(WANG C Y. Group Clustering and Recommendation Based on Nash Equilibrium. Master Dissertation. Nanjing, China: Nanjing University of Posts and Telecommunications, 2020.)