Differentially Private k-Nearest Neighbor Missing Data Imputation

被引：4

作者：

Clifton, Chris ^{[1
]}

Hanson, Eric J. ^{[2
]}

Merrill, Keith ^{[3
]}

Merrill, Shawn ^{[1
]}

机构：

[1] Purdue Univ, 305 N Univ St, W Lafayette, IN 47906 USA

[2] Univ Quebec Montreal, Lab Combinatoire & Informat Math, Montreal, PQ H3C 3P8, Canada

[3] Brandeis Univ, 415 South St, Waltham, MA 02453 USA

来源：

ACM TRANSACTIONS ON PRIVACY AND SECURITY | 2022年 / 25卷 / 03期

关键词：

Differential privacy; statistical disclosure limitation; private data cleaning; smooth sensitivity;

D O I：

10.1145/3507952

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Using techniques employing smooth sensitivity, we develop a method for k-nearest neighbor missing data imputation with differential privacy. This requires bounding the number of data incomplete tuples that can have their data complete "donor" changed by making a single addition or deletion to the dataset. The multiplicity of a single individual's impact on an imputed dataset necessarily means our mechanisms require the addition of more noise than mechanisms that ignore missing data, but we show empirically that this is significantly outweighed by the bias reduction from imputing missing data.

引用

页数：23

共 50 条

[1] K-Nearest Neighbor (K-NN) based Missing Data Imputation
Murti, Della Murbarani Prawidya
Wibawa, Aji Prasetya
Akbar, Muhammad Iqbal
Ianto, Utomo Puj
2019 5TH INTERNATIONAL CONFERENCE ON SCIENCE ININFORMATION TECHNOLOGY (ICSITECH): EMBRACING INDUSTRY 4.0 - TOWARDS INNOVATION IN CYBER PHYSICAL SYSTEM, 2019, : 83 - 88
[2] Imputation of missing values in well log data using k-nearest neighbor collaborative filtering
Kim, Min Jun
Cho, Yongchae
COMPUTERS & GEOSCIENCES, 2024, 193
[3] Handling Missing Strain (Rate) Curves Using K-Nearest Neighbor Imputation
Tabassian, Mahdi
Alessandrini, Martino
Jasaityte, Ruta
De Marchi, Luca
Masetti, Guido
D'hooge, Jan
2016 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS), 2016,
[4] A novel ranked k-nearest neighbors algorithm for missing data imputation
Khan, Yasir
Shah, Said Farooq
Asim, Syed Muhammad
JOURNAL OF APPLIED STATISTICS, 2024,
[5] TOBMI: trans-omics block missing data imputation using a k-nearest neighbor weighted approach
Dong, Xuesi
Lin, Lijuan
Zhang, Ruyang
Zhao, Yang
Christiani, David C.
Wei, Yongyue
Chen, Feng
BIOINFORMATICS, 2019, 35 (08) : 1278 - 1283
[6] Building K-nearest neighbor classifiers on vertically partitioned private data
Zhan, J
Chang, LW
2005 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING, VOLS 1 AND 2, 2005, : 708 - 711
[7] Comparative Analysis of K-Nearest Neighbor and Modified K-Nearest Neighbor Algorithm for Data Classification
Okfalisa
Mustakim
Gazalba, Ikbal
Reza, Nurul Gayatri Indah
2017 2ND INTERNATIONAL CONFERENCES ON INFORMATION TECHNOLOGY, INFORMATION SYSTEMS AND ELECTRICAL ENGINEERING (ICITISEE): OPPORTUNITIES AND CHALLENGES ON BIG DATA FUTURE INNOVATION, 2017, : 294 - 298
[8] How distance metrics influence missing data imputation with k-nearest neighbours
Santos, Miriam Seoane
Abreu, Pedro Henriques
Wilk, Szymon
Santos, Joao
PATTERN RECOGNITION LETTERS, 2020, 136 (136) : 111 - 119
[9] Combining Fourier and lagged k-nearest neighbor imputation for biomedical time series data
Rahman, Shah Atiqur
Huang, Yuxiao
Claassen, Jan
Heintzman, Nathaniel
Kleinberg, Samantha
JOURNAL OF BIOMEDICAL INFORMATICS, 2015, 58 : 198 - 207
[10] On the Use of Weighted k-Nearest Neighbors for Missing Value Imputation
Lim, Chanhui
Kim, Dongjae
KOREAN JOURNAL OF APPLIED STATISTICS, 2015, 28 (01) : 23 - 31

← 1 2 3 4 5 →