A federated learning framework based on transfer learning and knowledge distillation for targeted advertising

被引:0
作者
Su, Caiyu [1 ]
Wei, Jinri [1 ]
Lei, Yuan [2 ]
Li, Jiahui [3 ]
机构
[1] Guangxi Vocat & Tech Inst Ind, Nanning, Guangxi, Peoples R China
[2] Univ Pendidikan Sultan Idris, Tanjong Malim, Malaysia
[3] Guangxi Univ Foreign Languages, Nanning, Guangxi, Peoples R China
关键词
Federated learning; Transfer learning; Targeted advertising; Maximum mean difference; Knowledge distillation;
D O I
10.7717/peerj-cs.1496
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The rise of targeted advertising has led to frequent privacy data leaks, as advertisers are reluctant to share information to safeguard their interests. This has resulted in isolated data islands and model heterogeneity challenges. To address these issues, we have proposed a C-means clustering algorithm based on maximum average difference to improve the evaluation of the difference in distribution between local and global parameters. Additionally, we have introduced an innovative dynamic selection algorithm that leverages knowledge distillation and weight correction to reduce the impact of model heterogeneity. Our framework was tested on various datasets and its performance was evaluated using accuracy, loss, and AUC (area under the ROC curve) metrics. Results showed that the framework outperformed other models in terms of higher accuracy, lower loss, and better AUC while requiring the same computation time. Our research aims to provide a more reliable, controllable, and secure data sharing framework to enhance the efficiency and accuracy of targeted advertising.
引用
收藏
页数:27
相关论文
共 42 条
[1]   Reminder Care System: An Activity-Aware Cross-Device Recommendation System [J].
Altulyan, May S. ;
Huang, Chaoran ;
Yao, Lina ;
Wang, Xianzhi ;
Kanhere, Salil ;
Cao, Yunajiang .
ADVANCED DATA MINING AND APPLICATIONS, ADMA 2019, 2019, 11888 :207-220
[2]   Reminder of the First Paper on Transfer Learning in Neural Networks, 1976 [J].
Bozinovski, Stevo .
INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS, 2020, 44 (03) :291-302
[3]  
Chen Dingfan, 2020, Advances in Neural Information Processing Systems, V33
[4]  
Chung K, 2021, 35 INT C INFORM NETW
[5]   Investigating Generalized Performance of Data-Constrained Supervised Machine Learning Models on Novel, Related Samples in Intrusion Detection [J].
D'hooge, Laurens ;
Verkerken, Miel ;
Wauters, Tim ;
De Turck, Filip ;
Volckaert, Bruno .
SENSORS, 2023, 23 (04)
[6]   A Boosting-Aided Adaptive Cluster-Based Undersampling Approach for Treatment of Class Imbalance Problem [J].
Devi, Debashree ;
Namasudra, Suyel ;
Kadry, Seifedine .
INTERNATIONAL JOURNAL OF DATA WAREHOUSING AND MINING, 2020, 16 (03) :60-86
[7]   Pricing and personal data collection strategies of online platforms in the face of privacy concerns [J].
Duan, Yongrui ;
Ge, Yao ;
Feng, Yixuan .
ELECTRONIC COMMERCE RESEARCH, 2022, 22 (02) :539-559
[8]   Clustering for Private Interest-based Advertising [J].
Epasto, Alessandro ;
Medina, Andres Munoz ;
Avery, Steven ;
Bai, Yijian ;
Busa-Fekete, Robert ;
Carey, C. J. ;
Gao, Ya ;
Guthrie, David ;
Ghosh, Subham ;
Ioannidis, James ;
Jiao, Junyi ;
Lacki, Jakub ;
Lee, Jason ;
Mauser, Arne ;
Milch, Brian ;
Mirrokni, Vahab ;
Ravichandran, Deepak ;
Shi, Wei ;
Spero, Max ;
Sun, Yunting ;
Syed, Umar ;
Vassilvitskii, Sergei ;
Wang, Shuo .
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, :2802-2810
[9]  
Fang B., 2022, Journal of Computational and Cognitive Engineering, V1, P174, DOI DOI 10.47852/BONVIEWJCCE2202319
[10]   ST-SIGMA: Spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting [J].
Fang, Yang ;
Luo, Bei ;
Zhao, Ting ;
He, Dong ;
Jiang, Bingbing ;
Liu, Qilie .
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2022, 7 (04) :744-757