A Privacy-Aware Bayesian Approach for Combining Classifier and Cluster Ensembles

TL;DR

This paper presents a privacy-aware Bayesian method that effectively combines classifier and cluster ensemble results for semi-supervised learning across distributed data sites with sharing restrictions.

Contribution

It introduces a novel Bayesian framework for ensemble combination that respects data privacy constraints in distributed environments.

Findings

Achieves good classification accuracy under privacy constraints

Effectively combines classifier and cluster ensemble results

Applicable to semi-supervised and transductive learning scenarios

Abstract

This paper introduces a privacy-aware Bayesian approach that combines ensembles of classifiers and clusterers to perform semi-supervised and transductive learning. We consider scenarios where instances and their classification/clustering results are distributed across different data sites and have sharing restrictions. As a special case, the privacy aware computation of the model when instances of the target data are distributed across different data sites, is also discussed. Experimental results show that the proposed approach can provide good classification accuracies while adhering to the data/model sharing constraints.