Towards Privacy-Preserving Model Selection

  • Zhiqiang Yang
  • Sheng Zhong
  • Rebecca N. Wright
Conference paper

DOI: 10.1007/978-3-540-78478-4_8

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4890)
Cite this paper as:
Yang Z., Zhong S., Wright R.N. (2008) Towards Privacy-Preserving Model Selection. In: Bonchi F., Ferrari E., Malin B., Saygin Y. (eds) Privacy, Security, and Trust in KDD. Lecture Notes in Computer Science, vol 4890. Springer, Berlin, Heidelberg

Abstract

Model selection is an important problem in statistics, machine learning, and data mining. In this paper, we investigate the problem of enabling multiple parties to perform model selection on their distributed data in a privacy-preserving fashion without revealing their data to each other. We specifically study cross validation, a standard method of model selection, in the setting in which two parties hold a vertically partitioned database. For a specific kind of vertical partitioning, we show how the participants can carry out privacy-preserving cross validation in order to select among a number of candidate models without revealing their data to each other.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Zhiqiang Yang
    • 1
  • Sheng Zhong
    • 2
  • Rebecca N. Wright
    • 3
  1. 1.Department of Computer ScienceStevens Institute of TechnologyHobokenUSA
  2. 2.Department of Computer ScienceSUNY Buffalo, BuffaloNYUSA
  3. 3.Department of Computer Science and DIMACSRutgers UniversityPiscatawayUSA

Personalised recommendations