Affordable Access

deepdyve-link
Publisher Website

Federated Ensemble Regression Using Classification

Authors
  • Orhobor, Oghenejokpeme I.1
  • Soldatova, Larisa N.2
  • King, Ross D.1, 3, 4
  • 1 University of Cambridge,
  • 2 University of London,
  • 3 The Alan Turing Institute,
  • 4 Chalmers University of Technology,
Type
Published Article
Journal
Discovery Science
Publication Date
Sep 19, 2020
Volume
12323
Pages
325–339
Identifiers
DOI: 10.1007/978-3-030-61527-7_22
PMCID: PMC7556384
Source
PubMed Central
Keywords
License
Unknown

Abstract

Ensemble learning has been shown to significantly improve predictive accuracy in a variety of machine learning problems. For a given predictive task, the goal of ensemble learning is to improve predictive accuracy by combining the predictive power of multiple models. In this paper, we present an ensemble learning algorithm for regression problems which leverages the distribution of the samples in a learning set to achieve improved performance. We apply the proposed algorithm to a problem in precision medicine where the goal is to predict drug perturbation effects on genes in cancer cell lines. The proposed approach significantly outperforms the base case.

Report this publication

Statistics

Seen <100 times