DIFFERENTIALLY-PRIVATE CANONICAL CORRELATION ANALYSIS

被引：0

作者：

Imtiaz, Hafiz ^{[1
]}

Sarwate, Anand D. ^{[1
]}

机构：

[1] Rutgers State Univ, Dept Elect & Comp Engn, 94 Brett Rd, Piscataway, NJ 07302 USA

来源：

2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017) | 2017年

关键词：

differential-privacy; canonical correlation analysis; multi-view learning; clustering; dimension reduction; BLIND SOURCE SEPARATION; ALGORITHM; FMRI;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we propose a differentially-private canonical correlation analysis algorithm. Canonical correlation analysis (CCA) is often used in clustering applications for multi-view data. CCA finds subspaces for each view such that projecting each of the views onto these subspaces simultaneously reduces the dimension and maximizes correlation. Differential-privacy is a framework for understanding the risk of inferring the data input to the algorithm based on the output. We investigate the performance of the proposed algorithm with varying privacy parameters and database parameters on synthetic and real data. Our results show that it is possible to have meaningful privacy with very good utility even for strict privacy guarantees.

引用

页码：283 / 287

页数：5

共 50 条

[31] Differentially-Private Logistic Regression for Detecting Multiple-SNP Association in GWAS Databases
Yu, Fei
Rybar, Michal
Uhler, Caroline
Fienberg, Stephen E.
PRIVACY IN STATISTICAL DATABASES, PSD 2014, 2014, 8744 : 170 - 184
[32] Differentially-Private Distributed Fault Diagnosis for Large-Scale Nonlinear Uncertain Systems
Rostampour, Vahab
Ferrari, Riccardo
Teixeira, Andre M. H.
Keviczky, Tamas
IFAC PAPERSONLINE, 2018, 51 (24): : 975 - 982
[33] Histogramming Privately Ever After: Differentially-Private Data-Dependent Error Bound Optimisation
Fanaeepour, Maryam
Rubinstein, Benjamin I. P.
2018 IEEE 34TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE), 2018, : 1204 - 1207
[34] Differentially-Private "Draw and Discard" Machine Learning: Training Distributed Model from Enormous Crowds
Pihur, Vasyl
Korolova, Aleksandra
Liu, Frederick
Sankuratripati, Subhash
Yung, Moti
Huang, Dachuan
Zeng, Ruogu
CYBER SECURITY, CRYPTOLOGY, AND MACHINE LEARNING, 2022, 13301 : 468 - 486
[35] D2-PSD: Dynamic Differentially-Private Spatial Decomposition in Collaboration With Edge Server
Sasada, Taisho
Taenaka, Yuzo
Kadobayashi, Youki
IEEE ACCESS, 2024, 12 : 156307 - 156326
[36] Privacy-Accuracy Trade-Off in Differentially-Private Distributed Classification: A Game Theoretical Approach
Xu, Lei
Jiang, Chunxiao
Qian, Yi
Li, Jianhua
Zhao, Youjian
Ren, Yong
IEEE TRANSACTIONS ON BIG DATA, 2021, 7 (04) : 770 - 783
[37] Differentially-Private Federated Learning with Long-Term Budget Constraints Using Online Lagrangian Descent
Odeyomi, Olusola T.
Zaruba, Gergely
2021 IEEE WORLD AI IOT CONGRESS (AIIOT), 2021, : 1 - 6
[38] On Measure Transformed Canonical Correlation Analysis
Todros, Koby
Hero, Alfred O., III
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2012, 60 (09) : 4570 - 4585
[39] Universum Discriminant Canonical Correlation Analysis
Chen, Xiaohong
Yin, Hujun
Hu, Menglei
Wang, Liping
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2017, 2017, 10585 : 560 - 570
[40] Permutation inference for canonical correlation analysis
Winkler, Anderson M.
Renaud, Olivier
Smith, Stephen M.
Nichols, Thomas E.
NEUROIMAGE, 2020, 220

← 1 2 3 4 5 →