[1]王健宗,肖京,朱星华,等.联邦推荐系统的协同过滤冷启动解决方法[J].智能系统学报,2021,16(1):178-185.[doi:10.11992/tis.202009032]
WANG Jianzong,XIAO Jing,ZHU Xinghua,et al.Cold starts in collaborative filtering for federated recommender systems[J].CAAI Transactions on Intelligent Systems,2021,16(1):178-185.[doi:10.11992/tis.202009032]
点击复制
WANG Jianzong,XIAO Jing,ZHU Xinghua,et al.Cold starts in collaborative filtering for federated recommender systems[J].CAAI Transactions on Intelligent Systems,2021,16(1):178-185.[doi:10.11992/tis.202009032]
联邦推荐系统的协同过滤冷启动解决方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第1期
页码:
178-185
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2021-01-05
- Title:
- Cold starts in collaborative filtering for federated recommender systems
- Keywords:
- federated learning; privacy protection; data island; recommender system; collaborative filtering; cold start; machine learning; secure inner product
- 分类号:
- TP391
- 摘要:
- 基于联邦学习的推荐系统可以在保护用户隐私的情况下，联合多方数据，提升推荐系统的性能，已经成为推荐领域的研究热点之一。联邦协同过滤是联邦推荐系统中最经典及最常用的算法之一。然而，针对联邦协同过滤系统的冷启动问题的研究工作相对较少。针对这一问题，本文提出了一种基于安全内积协议的解决方案。具体地，在系统中添加新用户或新物品时，联合多方评分矩阵，利用安全内积的方法，对多方数据进行相似矩阵的求解，从而完成推荐输出。本文在MovieLens数据集上对所述方法进行了验证。结果表明：本方法能够有效解决基于相似度的协同过滤中的冷启动问题，并且推荐效果也会依据多方数据分布的比例变化。
- Abstract:
- Recommender systems based on federated learning has become one of the research hotspots in the recommender field. However, few studies focused on the cold start problem of federated recommender systems. Under the framework of federated learning, we propose a novel collaborative filtering algorithm for its solution: through involving more rating matrices, we can get a similarity matrix with secure inner product method, and implement the recommendation for new users to the system. In this work, we verify the performance of our method on MovieLens. The results show that our proposal is effective in solving the cold start problem in similarity-based collaborative filtering, and the recommendation effects vary according to the data distribution among different parties.
- 参考文献/References:
-
[1] ALBRECHT J P. How the GDPR will change the world[J]. European data protection law review, 2016, 2(3):287-289.
[2] SHI E, CHAN T H H, RIEFFEL E, et al. Distributed private data analysis:lower bounds and practical constructions[J]. ACM transactions on algorithms, 2017, 13(4):50.
[3] KIM S, KIM J, KOO D, et al. Efficient privacy-preserving matrix factorization via fully homomorphic encryption:extended Abstract[C]//Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security. Xi’an, China, 2016:617-628.
[4] SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web. Hong Kong, China, 2001:285-295.
[5] HERLOCKER J L, KONSTAN J A, BORCHERS A, et al. An algorithmic framework for performing collaborative filtering[C]//Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. California, Berkeley, USA, 1999:230-237.
[6] KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8):30-37.
[7] RENNIE J D M, SREBRO N. Fast maximum margin matrix factorization for collaborative prediction[C]//Proceedings of the 22nd International Conference on Machine Learning. New York, USA, 2005:713-719.
[8] KOBSA A. Privacy-enhanced web personalization[M]. BRUSILOVSKY P, KOBSA A, NEJDL W. The Adaptive Web:Methods and Strategies of Web Personalization. Berlin:Springer, 2007:628-670.
[9] JECKMANS A, TANG Qiang, HARTEL P. Privacy-preserving collaborative filtering based on horizontally partitioned dataset[C]//Proceedings of 2012 International Conference on Collaboration Technologies and Systems. Denver, USA, 2012.
[10] QIAO Yu, LI Lingjuan. Research on resolving strategies of the cold start problem of recommendation system[J]. Computer technology and development, 2018, 28(2):83-87.
[11] YANG Qiang, LIU Yang, CHEN Tianjian, et al. Federated machine learning:concept and applications[J]. ACM transactions on intelligent systems and technology, 2019, 10(2):12.
[12] 乔雨, 李玲娟. 推荐系统冷启动问题解决策略研究[J]. 计算机技术与发展, 2018, 28(2):83-87
QIAO Yu, LI Lingjuan. Research on solution of solving cold start problem in recommender systems[J]. Computer technology and development, 2018, 28(2):83-87
[13] ZHAO Lingchen, NI Lihao, HU Shengshan, et al. InPrivate digging:enabling tree-based distributed data mining with differential privacy[C]//Proceedings of 2018 IEEE Conference on Computer Communications. Honolulu, USA, 2018:2087-2095.
[14] SMITH V, CHIANG C K, SANJABI M, et al. Federated multi-task learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, USA, 2017:4427-4437.
[15] HSU C C, YEH M Y, LIN Shude. A general framework for implicit and explicit social recommendation[J]. IEEE transactions on knowledge and data engineering, 2018, 30(12):2228-2241.
[16] CHEN Shulong, PENG Yuxing. Matrix factorization for recommendation with explicit and implicit feedback[J]. Knowledge-based systems, 2018, 158:109-117.
[17] JAWAHEER G, SZOMSZOR M, KOSTKOVA P. Comparison of implicit and explicit feedback from an online music recommendation service[C]//Proceedings of the 1st International Workshop on Information Heterogeneity and Fusion in Recommender Systems. New York, USA, 2010:47-51.
[18] PAZZANI M J, BILLSUS D. Content-based recommendation systems[M]. BRUSILOVSKY P, KOBSA A, NEJDL W. The Adaptive Web:Methods and Strategies of Web Personalization. Berlin, Heidelberg, Germany:Springer, 2007:325-341.
[19] BURKE R. Knowledge-based recommender systems[J]. Encyclopedia of library and information systems, 2000, 69(S32):175-186.
[20] WANG Jizhe, HUANG Pipei, ZHAO Huan, et al. Billion-scale commodity embedding for E-commerce recommendation in Alibaba[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London, United Kingdom, 2018:839-848.
[21] HWANGBO H, KIM Y S, CHA K J. Recommendation system development for fashion retail E-commerce[J]. Electronic commerce research and applications, 2018, 28:94-101.
[22] HERLOCKER J L, KONSTAN J A, RIEDL J. Explaining collaborative filtering recommendations[C]//Proceedings of the 2000 ACM Conference on Computer Supported Cooperative Work. Pennsylvania, Philadelphia, USA, 2000:241-250.
[23] SUBRAMANIYASWAMY V, LOGESH R, CHANDRASHEKHAR M, et al. A personalised movie recommendation system based on collaborative filtering[J]. International journal of high performance computing and networking, 2017, 10(1/2):54-63.
[24] ZHENG E, KONDO G Y, ZILORA S, et al. Tag-aware dynamic music recommendation[J]. Expert systems with applications, 2018, 106:244-251.
[25] ZHENG Guanjie, ZHANG Fuzheng, ZHENG Zihan, et al. DRN:a deep reinforcement learning framework for news recommendation[C]//Proceedings of the 2018 World Wide Web Conference. Lyon, France, 2018:167-176.
[26] COLOMO-PALACIOS R, GARCíA-PE?ALVO F J, STANTCHEV V, et al. Towards a social and context-aware mobile recommendation system for tourism[J]. Pervasive and mobile computing, 2017, 38:505-515.
[27] GENTRY C. A fully homomorphic encryption scheme[D]. Palo Alto:Stanford University, 2009.
[28] CANNY J. Collaborative filtering with privacy via factor analysis[C]//Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Tampere, Finland, 2002:238-245.
[29] CHEN Chaochao, ZHOU Jun, WU Bingzhe, et al. Practical privacy preserving POI recommendation[J]. ACM transactions on intelligent systems and technology, 2020, 11(5):52.
[30] CHEN Chaochao, LIU Ziqi, ZHAO Peilin, et al. Privacy preserving point-of-interest recommendation using decentralized matrix factorization[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA, 2018:257-264.
[31] ERKIN Z, BEYE M, VEUGEN T, et al. Efficiently computing private recommendations[C]//Proceedings of 2011 IEEE International Conference on Acoustics, Speech and Signal Processing. Prague, Czech Republic, 2011:5864-5867.
[32] KATARYA R, VERMA O P. Effective collaborative movie recommender system using asymmetric user similarity and matrix factorization[C]//Proceedings of 2016 International Conference on Computing, Communication and Automation. Noida, India, 2016:71-75.
[33] HERLOCKER J L, KONSTAN J A, BORCHERS A, et al. An algorithmic framework for performing collaborative filtering[C]//Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. California, Berkeley, USA, 1999:230-237.
[34] GASCON A, SCHOPPMANN P, BALLE B, et al. Secure linear regression on vertically partitioned datasets[J]. IACR cryptology ePrint archive, 2016, 2016:892.
[35] HARPER F M, KONSTAN J A. The movielens datasets:history and context[J]. ACM transactions on interactive intelligent systems, 2015, 5(4):19.
[36] KOREN Y. Factorization meets the neighborhood:a multifaceted collaborative filtering model[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Nevada, Las Vegas, USA, 2008:426-434.
[37] NIKOLAENKO V, WEINSBERG U, IOANNIDIS S, et al. Privacy-preserving ridge regression on hundreds of millions of records[C]//Proceedings of 2013 IEEE Symposium on Security and Privacy. Berkeley, USA, 2013:334-348.
- 相似文献/References:
-
[1]吉根林,姚? 瑶.一种分布式隐私保护的密度聚类算法[J].智能系统学报,2009,4(2):137.
JI Gen-lin,YAO Yao.Densitybased privacy preserving distributed clustering algorithm[J].CAAI Transactions on Intelligent Systems,2009,4():137.
[2]张兴,陈昊.差分隐私的高维数据发布研究综述[J].智能系统学报,2021,16(6):989.[doi:10.11992/tis.202104023]
ZHANG Xing,CHEN Hao.A research review of high-dimensional data publishing based on a differential privacy model[J].CAAI Transactions on Intelligent Systems,2021,16():989.[doi:10.11992/tis.202104023]
[3]窦勇敢,袁晓彤.基于隐式随机梯度下降优化的联邦学习[J].智能系统学报,2022,17(3):488.[doi:10.11992/tis.202106029]
DOU Yonggan,YUAN Xiaotong.Federated learning with implicit stochastic gradient descent optimization[J].CAAI Transactions on Intelligent Systems,2022,17():488.[doi:10.11992/tis.202106029]
备注/Memo
收稿日期:2020-09-23。
基金项目:国家重点研发计划“云计算和大数据”重点专项(2018YFB1003503)；国家重点研发计划“高性能计算”重点专项(2018YFB0204400)；国家重点研发计划“现代服务业共性关键技术研发及应用示范”专项(2017YFB1401202)
作者简介:王健宗，高级工程师，博士，主要研究方向为联邦学习算法、金融智能平台。主持国家重点研发计划基金项目3项、校企联合课题2项，授权发明专利100余项。发表学术论文50余篇，出版著作3部;肖京，教授级高级工程师，博士，主要研究方向为人工智能与大数据分析挖掘。国际授权专利101项，授权国内发明专利109项。2019 年吴文俊人工智能科学技术奖“杰出贡献奖”获得者，发表学术论文130余篇;朱星华，博士研究生，主要研究方向为联邦学习、机器视觉算法
通讯作者:王健宗. E-mail：jzwang@188.com
更新日期/Last Update:
2021-02-25