Differentially Private Extreme Learning Machine

被引：0

作者：

Ono, Hajime ^{[1
]}

Tran Thi Phuong ^{[1
]}

Le Trieu Phong ^{[1
]}

机构：

[1] Natl Inst Informat & Commun Technol NICT, 4-2-1 Nukui Kitamachi, Koganei, Tokyo 1848795, Japan

来源：

MODELING DECISIONS FOR ARTIFICIAL INTELLIGENCE, MDAI 2024 | 2024年 / 14986卷

关键词：

Differential privacy; Extreme Learning Machine; Generalization performance; REGRESSION;

D O I：

10.1007/978-3-031-68208-7_14

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a novel algorithm, the Differentially Private Extreme Learning Machine (DPELM), which guarantees pure differential privacy. The differential privacy budget is determined solely by one parameter of the ELM model: the number of hidden nodes. We demonstrate the effectiveness of DPELM by showcasing its reasonable utility, including its strong generalization performance, across benchmark datasets. Furthermore, DPELM offers a user-friendly experience, as it eliminates the need to consider data dimensionality, gradient norms, or objective function sensitivities.

引用

页码：165 / 176

页数：12

共 14 条

[1] Deep Learning with Differential Privacy [J].

Abadi, Martin ;

Chu, Andy ;

Goodfellow, Ian ;

McMahan, H. Brendan ;

Mironov, Ilya ;

Talwar, Kunal ;

Zhang, Li .

CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, :308-318

[2]

Becker B., 1996, ADULT UCI MACHINE LE, DOI DOI 10.24432/C5XW20

[3] Secure Multi-party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data [J].

Catak, Ferhat Ozgur .

NEURAL INFORMATION PROCESSING, PT II, 2015, 9490 :337-345

[4]

Chaudhuri K, 2011, J MACH LEARN RES, V12, P1069

[5] Calibrating noise to sensitivity in private data analysis [J].

Dwork, Cynthia ;

McSherry, Frank ;

Nissim, Kobbi ;

Smith, Adam .

THEORY OF CRYPTOGRAPHY, PROCEEDINGS, 2006, 3876 :265-284

[6] Universal approximation using incremental constructive feedforward networks with random hidden nodes [J].

Huang, Guang-Bin ;

Chen, Lei ;

Siew, Chee-Kheong .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (04) :879-892

[7] What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt's Dream and John von Neumann's Puzzle [J].

Huang, Guang-Bin .

COGNITIVE COMPUTATION, 2015, 7 (03) :263-278

[8] Extreme Learning Machine for Regression and Multiclass Classification [J].

Huang, Guang-Bin ;

Zhou, Hongming ;

Ding, Xiaojian ;

Zhang, Rui .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2012, 42 (02) :513-529

[9]

Kuri S., 2017, 2017 IEEE S SERIES C, P1, DOI [10.1109/SSCI.2017.8285190, DOI 10.1109/SSCI.2017.8285190]

[10] Optimizing extreme learning machines via ridge regression and batch intrinsic plasticity [J].

Neumann, Klaus ;

Steil, Jochen J. .

NEUROCOMPUTING, 2013, 102 :23-30

← 1 2 →