Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations
Abstract
Dimensionality Reduction is a commonly used element in a machine learning pipeline that helps to extract important features from high-dimensional data. In this work, we explore an alternative federated learning system that enables integration of dimensionality reduced representations of distributed data prior to a supervised learning task, thus avoiding model sharing among the parties. We compare the performance of this approach on image classification tasks to three alternative frameworks: centralized machine learning, individual machine learning, and Federated Averaging, and analyze potential use cases for a federated learning system without model sharing. Our results show that our approach can achieve similar accuracy as Federated Averaging and performs better than Federated Averaging in a small-user setting.
Cite
@article{arxiv.2011.06803,
title = {Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations},
author = {Anna Bogdanova and Akie Nakai and Yukihiko Okada and Akira Imakura and Tetsuya Sakurai},
journal= {arXiv preprint arXiv:2011.06803},
year = {2020}
}
Comments
6 pages with 4 figures. To be presented at the Workshop on Federated Learning for Data Privacy and Confidentiality in Conjunction with IJCAI 2020 (FL-IJCAI'20)