PaDPaF: Partial Disentanglement with Partially-Federated GANs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Almansoori, Abdulla Jasem, Horváth, Samuel, Takáč, Martin
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929361147396096
author Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
author_facet Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
contents Federated learning has become a popular machine learning paradigm with many potential real-life applications, including recommendation systems, the Internet of Things (IoT), healthcare, and self-driving cars. Though most current applications focus on classification-based tasks, learning personalized generative models remains largely unexplored, and their benefits in the heterogeneous setting still need to be better understood. This work proposes a novel architecture combining global client-agnostic and local client-specific generative models. We show that using standard techniques for training federated models, our proposed model achieves privacy and personalization by implicitly disentangling the globally consistent representation (i.e. content) from the client-dependent variations (i.e. style). Using such decomposition, personalized models can generate locally unseen labels while preserving the given style of the client and can predict the labels for all clients with high accuracy by training a simple linear classifier on the global content features. Furthermore, disentanglement enables other essential applications, such as data anonymization, by sharing only the content. Extensive experimental evaluation corroborates our findings, and we also discuss a theoretical motivation for the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2212_03836
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle PaDPaF: Partial Disentanglement with Partially-Federated GANs
Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
Computer Vision and Pattern Recognition
Machine Learning
Federated learning has become a popular machine learning paradigm with many potential real-life applications, including recommendation systems, the Internet of Things (IoT), healthcare, and self-driving cars. Though most current applications focus on classification-based tasks, learning personalized generative models remains largely unexplored, and their benefits in the heterogeneous setting still need to be better understood. This work proposes a novel architecture combining global client-agnostic and local client-specific generative models. We show that using standard techniques for training federated models, our proposed model achieves privacy and personalization by implicitly disentangling the globally consistent representation (i.e. content) from the client-dependent variations (i.e. style). Using such decomposition, personalized models can generate locally unseen labels while preserving the given style of the client and can predict the labels for all clients with high accuracy by training a simple linear classifier on the global content features. Furthermore, disentanglement enables other essential applications, such as data anonymization, by sharing only the content. Extensive experimental evaluation corroborates our findings, and we also discuss a theoretical motivation for the proposed approach.
title PaDPaF: Partial Disentanglement with Partially-Federated GANs
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2212.03836