Computer Science

Computer Science ›› 2022, Vol. 49 ›› Issue (12): 66-73.doi: 10.11896/jsjkx.220600034

• Federated Leaming • Previous Articles     Next Articles

FL-GRM:Gamma Regression Algorithm Based on Federated Learning

GUO Yan-qing1, LI Yu-hang1, WANG Wan-wan2, FU Hai-yan1, WU Ming-kan1, LI Yi1   

  1. 1 School of Information and Communication Engineering,Dalian University of Technology,Dalian,Liaoning 116024,China
    2 Research Center of InsightOne Tech Co.,Ltd.,Beijing 100028,China
  • Received:2022-06-06 Revised:2022-08-29 Online:2022-12-15 Published:2022-12-14
  • About author:GUO Yan-qing,born in 1980,Ph.D,professor, Ph.D supervisor.His main research interests include machine lear-ning,computer vision and cyberspace security.FU Hai-yan,born in 1981,Ph.D,senior engineer.Her main research interests include federated learning,image retrieval and computer vision.
  • Supported by:
    National Natural Science Foundation of China(62076052,62106037,U1936117),Fundamental Research Funds for the Central Universities(DUT20TD110,DUT20RC(3)088),Major Program of the National Social Science Foundation of China(19ZDA127) and Open Project Program of the National Laboratory of Pattern Recognition(NLPR)(202100032).

PDF (PC)

382

Abstract: People commonly hypothesize that an independent variable follows a Gamma distribution in many areas,including hydrology,meteorology and insurance claim.Under the Gamma distribution assumption,Gamma regression model enables an outstanding fitting effect,compared with multivariate linear-regression model.Previous studies may be able to obtain a Gamma regression model trained only on a public dataset.However,when the datasets are provided by multiple parties,how to seek to address the problem of data privacy by training Gamma regression model without exchanging the data itself? A secure multi-party federated Gamma regression algorithm has been applied to this area.Firstly,the log-likelihood function is derived with the iterative method.Secondly,the link function is determined according to the fact,and the gradient updating strategy is constructed by the loss function.Finally,the parameters with homomorphic encryption are updated,then the training is completed.The model is tested on two public datasets,and the results show that under the premise of privacy protection our method can effectively use the value of multi-party data to generate Gamma regression model.The fitting performance of our method is better than that of Gamma regression model implements in a single part,and is close to the result yielded by centralized data learning model.

Key words: Federated learning, Gamma regression, Homomorphic encryption, Privacy protection, Secure multi-party computation

CLC Number: 

  • TP181
[1]NELDE R,JOHN A,ROBERT W W.Generalized linear models[J].Journal of the Royal Statistical Society:Series A(General),1972,135(3):370-384.
[2]ENGLAND P D,RICHARD J V.Stochastic claims reserving in general insurance[J].British Actuarial Journal,2002,8(3):443-518.
[3]AMIN M,QASIM M,AMANUM,et al.Performance of someridge estimators for the gamma regression model[J].Statistical Papers,2020,61(3):997-1026.
[4]WU Z J.The Establishment of SPI_GD Drought index and the research on its test and application[D].Lanzhou:Lanzhou University,2017.
[5]MA X M,LUO Z Q.Human activity intensity time and space change research on haba snow mountain nature reserve[J].Journal of AnhuiAgricultural Sciences,2015,43(19):205-208.
[6]PAYNTER S,NACHABE M.Regional scale spatio-temporalconsistency of precipitation variables related to water resource management and planning[J].Meteorological Applications,2010,16(3):413-423.
[7]GONG M D.The empirical research on agricultural insuranceclassification ratemaking[D].Hunan:Hunan University,2011.
[8]ZHONG Z,MENG S W.Comparison and application of gamma regression and lognormla regression[J].Journal of Applied Statistics and Management,2010,29(3):430-436.
[9]LI T,SANJABI M,BEIRAMI A,et al.Fair resource allocation in federated learning[J].arXiv:1905.10497,2022.
[10]MCMAHAN B,MOORE E,RAMAGE D,et al.Communication-efficient learning of deep networks from decentralized data[C]//Artificial Intelligence and Statistics.PMLR,2017:1273-1282.
[11]MCMAHAN H B,MOORE E,RAMAGE D,et al.Federated learning of deep networks using model averaging[J].arXiv:1602.05629,2016.
[12]GAO D,JU C,WEI X,et al.HHHFL:hierarchical heteroge-neous horizontal federated learning for electroence phalography[J].arXiv:1909.05784,2019.
[13]LIU Y,KANG Y,ZHANG X,et al.A communication efficient vertical federated learning framework[J].arXiv:1912.11187,2019.
[14]SHREYA S,XING C,YANG L,et al.Secure and efficient fede-rated transfer learning[C].In 2019 IEEE International Confe-rence on Big Data(Big Data).2019:2569-2576.
[15]HARD A,RAO K,MATHEWS R,et al.Federated learning for mobile keyboard prediction[J].arXiv:1811.03604,2018.
[16]LI T,ANIT K S,AMEET T,et al.Federated learning:Challenges,methods,and future directions[J].IEEE Signal Processing Magazine,2020,37(3):50-60.
[17]KAIROUZ P,MCMAHAN H B,AVENT B.Advances and open problems in federated learning[J].Foundations and Trends© in Machine Learning,2021,14(1/2):1-210.
[18]MOTHUKURI V,PARIZI R M,POURIYEH S,et al.A survey on security and privacy of federated learning[J].Future Generation Computer Systems,2021,115:619-640.
[19]WANG J Z,KONG L W,HUANG Z C,et al.Summary of fede-rated learning algorithms[J].Big Data,2020,6(6):64-82.
[20]YANG K,FAN T,CHEN T J,et al.A quasinewton methodbased vertical federated learning framework for logistic regression[J].arXiv:1912.00513,2019.
[21]YANG S,REN B,ZHOU X,et al.Parallel distributed logistic regression for vertical federated learning without thirdparty coordinator[J].arXiv:1911.09824,2019.
[22]LIU Y,LIU Y T,LIU Z,et al.Federated Forest[J].arXiv:1905.10053,2020.
[23]CHENG K,FAN T,JIN Y,et al.Secureboost:A lossless federated learning framework[J].IEEE Intelligent Systems,2021,36(6):87-98.
[24]YANG Q,LIU Y,CHEN T,et al.Federated machine learning:concept and applications[J].ACM Transactions on Intelligent Systems and Technology,2019,10(2):1-19.
[25]LI Q,WEN Z Y,WU Z M,et al.A survey on federated learning systems:vision,hype and reality for data privacy and protection[J].arXiv:1907.09693,2022.
[26]JAKUB K H,BRENDAN M,DANIEL R,et al.Federated optimization:distributed machine learning for on-device intelligence[J].arXiv:1610.02527,2022.
[27]WANG J Y,LIU Q H,LIANG H,et al.Tackling the objective inconsistency problem in heterogeneous federated optimization[C]//Advances in Neural Information Processing Systems.2020:7611-7623.
[28]LUO X,WU Y,XIAO X,et al.Feature inference attack on mo-del predictions in vertical federated learning[C]//International Conference on Data Engineering.2021:181-192.
[29]WANC P,CHEN Q.Robust federated learning with attack-adaptive aggregation[J].arXiv:2102.05257,2021.
[30]HAZRAT A,TANVIR A,MOWAFA H,et al.Federated Lear-ning and Internet of Medical Things－Opportunities and Challenges[J].Studies in Health Technology and Informatics,2022,295:201-204.
[31]WEN Y,CHEN M.Medical Data Sharing Scheme Combinedwith Federal Learning and Blockchain[J].Computer Enginee-ring,2022,48(5):145-153,161.
[32]WANG S S,CHEN J Y,LU Y N.COVID-19 chest CT image segmentation based on federated learning and blockchain[J].Journal of Jilin University,2021,51(6):2164-2173.
[33]PINKAS B,SCHNEIDER T,ZOHNER M.Scalable private set intersection based on OT extension[J].ACM Transactions on Privacy and Security(TOPS),2018,21(2):1-35.
[34]TANG Y Y.Gamma distribution and gamma regression[D].Yangzhou:Yangzhou University,2017.
[35]RIVEST R L,ADLEMAN L M,DERTOUZOS M L.On data banks and privacy homomorphisms[J].Foundations of secure computation,1978,4(11):169-180.
[1] LU Chen-yang, DENG Su, MA Wu-bin, WU Ya-hui, ZHOU Hao-hao. Federated Learning Based on Stratified Sampling Optimization for Heterogeneous Clients [J]. Computer Science, 2022, 49(9): 183-193.
[2] TANG Ling-tao, WANG Di, ZHANG Lu-fei, LIU Sheng-yun. Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy [J]. Computer Science, 2022, 49(9): 297-305.
[3] LYU You, WU Wen-yuan. Privacy-preserving Linear Regression Scheme and Its Application [J]. Computer Science, 2022, 49(9): 318-325.
[4] CHEN Ming-xin, ZHANG Jun-bo, LI Tian-rui. Survey on Attacks and Defenses in Federated Learning [J]. Computer Science, 2022, 49(7): 310-323.
[5] YAN Meng, LIN Ying, NIE Zhi-shen, CAO Yi-fan, PI Huan, ZHANG Lan. Training Method to Improve Robustness of Federated Learning [J]. Computer Science, 2022, 49(6A): 496-501.
[6] LU Chen-yang, DENG Su, MA Wu-bin, WU Ya-hui, ZHOU Hao-hao. Clustered Federated Learning Methods Based on DBSCAN Clustering [J]. Computer Science, 2022, 49(6A): 232-237.
[7] QIN Xiao-yue, HUANG Ru-wei, YANG Bo. NTRU Type Fully Homomorphic Encryption Scheme over Prime Power Cyclotomic Rings [J]. Computer Science, 2022, 49(5): 341-346.
[8] WANG Mei-shan, YAO Lan, GAO Fu-xiang, XU Jun-can. Study on Differential Privacy Protection for Medical Set-Valued Data [J]. Computer Science, 2022, 49(4): 362-368.
[9] LYU You, WU Wen-yuan. Linear System Solving Scheme Based on Homomorphic Encryption [J]. Computer Science, 2022, 49(3): 338-345.
[10] DU Hui, LI Zhuo, CHEN Xin. Incentive Mechanism for Hierarchical Federated Learning Based on Online Double Auction [J]. Computer Science, 2022, 49(3): 23-30.
[11] WANG Xin, ZHOU Ze-bao, YU Yun, CHEN Yu-xu, REN Hao-wen, JIANG Yi-bo, SUN Ling-yun. Reliable Incentive Mechanism for Federated Learning of Electric Metering Data [J]. Computer Science, 2022, 49(3): 31-38.
[12] ZHAO Luo-cheng, QU Zhi-hao, XIE Zai-peng. Study on Communication Optimization of Federated Learning in Multi-layer Wireless Edge Environment [J]. Computer Science, 2022, 49(3): 39-45.
[13] REN Hua, NIU Shao-zhang, WANG Mao-sen, YUE Zhen, REN Ru-yong. Homomorphic and Commutative Fragile Zero-watermarking Based on SVD [J]. Computer Science, 2022, 49(3): 70-76.
[14] ZOU Sai-lan, LI Zhuo, CHEN Xin. Study on Transmission Optimization for Hierarchical Federated Learning [J]. Computer Science, 2022, 49(12): 5-16.
[15] SHEN Zhen, ZHAO Cheng-gui. Storage Task Allocation Algorithm in Decentralized Cloud Storage Network [J]. Computer Science, 2022, 49(12): 17-21.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.