Privacy-preserving source separation for distributed data using independent component analysis

Hafiz Imtiaz, Rogers Silva, Bradley Baker, Sergey M. Plis, Anand D. Sarwate, Vince Daniel Calhoun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Building good feature representations and learning hidden source models typically requires large sample sizes. In many applications, however, the size of the sample at an individual data holder may not be sufficient. One such application is neuroimaging analyses for mental health disorders - there are many individual research groups, each with a moderate number of subjects. Pooling such data can enable efficient feature learning, but privacy concerns prevent sharing the underlying data. We propose a model for private feature learning in which the data holders share differentially private views of their respective datasets to enable collaborative learning of a joint feature map. We give an example of such an algorithm for independent component analysis (ICA) - a popular blind source separation algorithm used in neuroimaging analyses. Our algorithm is a differentially private version of the recently proposed distributed joint ICA algorithm. We evaluate the performance of this method on simulated functional magnetic resonance imaging (fMRI) data.

Original languageEnglish (US)
Title of host publication2016 50th Annual Conference on Information Systems and Sciences, CISS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages123-127
Number of pages5
ISBN (Electronic)9781467394574
DOIs
StatePublished - Apr 26 2016
Externally publishedYes
Event50th Annual Conference on Information Systems and Sciences, CISS 2016 - Princeton, United States
Duration: Mar 16 2016Mar 18 2016

Other

Other50th Annual Conference on Information Systems and Sciences, CISS 2016
CountryUnited States
CityPrinceton
Period3/16/163/18/16

Fingerprint

Source separation
Independent component analysis
Neuroimaging
Blind source separation
Health

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Imtiaz, H., Silva, R., Baker, B., Plis, S. M., Sarwate, A. D., & Calhoun, V. D. (2016). Privacy-preserving source separation for distributed data using independent component analysis. In 2016 50th Annual Conference on Information Systems and Sciences, CISS 2016 (pp. 123-127). [7460488] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISS.2016.7460488

Privacy-preserving source separation for distributed data using independent component analysis. / Imtiaz, Hafiz; Silva, Rogers; Baker, Bradley; Plis, Sergey M.; Sarwate, Anand D.; Calhoun, Vince Daniel.

2016 50th Annual Conference on Information Systems and Sciences, CISS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 123-127 7460488.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Imtiaz, H, Silva, R, Baker, B, Plis, SM, Sarwate, AD & Calhoun, VD 2016, Privacy-preserving source separation for distributed data using independent component analysis. in 2016 50th Annual Conference on Information Systems and Sciences, CISS 2016., 7460488, Institute of Electrical and Electronics Engineers Inc., pp. 123-127, 50th Annual Conference on Information Systems and Sciences, CISS 2016, Princeton, United States, 3/16/16. https://doi.org/10.1109/CISS.2016.7460488
Imtiaz H, Silva R, Baker B, Plis SM, Sarwate AD, Calhoun VD. Privacy-preserving source separation for distributed data using independent component analysis. In 2016 50th Annual Conference on Information Systems and Sciences, CISS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 123-127. 7460488 https://doi.org/10.1109/CISS.2016.7460488
Imtiaz, Hafiz ; Silva, Rogers ; Baker, Bradley ; Plis, Sergey M. ; Sarwate, Anand D. ; Calhoun, Vince Daniel. / Privacy-preserving source separation for distributed data using independent component analysis. 2016 50th Annual Conference on Information Systems and Sciences, CISS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 123-127
@inproceedings{b1ce874f650842b3ade56c25bf4b48ea,
title = "Privacy-preserving source separation for distributed data using independent component analysis",
abstract = "Building good feature representations and learning hidden source models typically requires large sample sizes. In many applications, however, the size of the sample at an individual data holder may not be sufficient. One such application is neuroimaging analyses for mental health disorders - there are many individual research groups, each with a moderate number of subjects. Pooling such data can enable efficient feature learning, but privacy concerns prevent sharing the underlying data. We propose a model for private feature learning in which the data holders share differentially private views of their respective datasets to enable collaborative learning of a joint feature map. We give an example of such an algorithm for independent component analysis (ICA) - a popular blind source separation algorithm used in neuroimaging analyses. Our algorithm is a differentially private version of the recently proposed distributed joint ICA algorithm. We evaluate the performance of this method on simulated functional magnetic resonance imaging (fMRI) data.",
author = "Hafiz Imtiaz and Rogers Silva and Bradley Baker and Plis, {Sergey M.} and Sarwate, {Anand D.} and Calhoun, {Vince Daniel}",
year = "2016",
month = "4",
day = "26",
doi = "10.1109/CISS.2016.7460488",
language = "English (US)",
pages = "123--127",
booktitle = "2016 50th Annual Conference on Information Systems and Sciences, CISS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Privacy-preserving source separation for distributed data using independent component analysis

AU - Imtiaz, Hafiz

AU - Silva, Rogers

AU - Baker, Bradley

AU - Plis, Sergey M.

AU - Sarwate, Anand D.

AU - Calhoun, Vince Daniel

PY - 2016/4/26

Y1 - 2016/4/26

N2 - Building good feature representations and learning hidden source models typically requires large sample sizes. In many applications, however, the size of the sample at an individual data holder may not be sufficient. One such application is neuroimaging analyses for mental health disorders - there are many individual research groups, each with a moderate number of subjects. Pooling such data can enable efficient feature learning, but privacy concerns prevent sharing the underlying data. We propose a model for private feature learning in which the data holders share differentially private views of their respective datasets to enable collaborative learning of a joint feature map. We give an example of such an algorithm for independent component analysis (ICA) - a popular blind source separation algorithm used in neuroimaging analyses. Our algorithm is a differentially private version of the recently proposed distributed joint ICA algorithm. We evaluate the performance of this method on simulated functional magnetic resonance imaging (fMRI) data.

AB - Building good feature representations and learning hidden source models typically requires large sample sizes. In many applications, however, the size of the sample at an individual data holder may not be sufficient. One such application is neuroimaging analyses for mental health disorders - there are many individual research groups, each with a moderate number of subjects. Pooling such data can enable efficient feature learning, but privacy concerns prevent sharing the underlying data. We propose a model for private feature learning in which the data holders share differentially private views of their respective datasets to enable collaborative learning of a joint feature map. We give an example of such an algorithm for independent component analysis (ICA) - a popular blind source separation algorithm used in neuroimaging analyses. Our algorithm is a differentially private version of the recently proposed distributed joint ICA algorithm. We evaluate the performance of this method on simulated functional magnetic resonance imaging (fMRI) data.

UR - http://www.scopus.com/inward/record.url?scp=84992406261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992406261&partnerID=8YFLogxK

U2 - 10.1109/CISS.2016.7460488

DO - 10.1109/CISS.2016.7460488

M3 - Conference contribution

AN - SCOPUS:84992406261

SP - 123

EP - 127

BT - 2016 50th Annual Conference on Information Systems and Sciences, CISS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -