Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jang, Jaeyeon, Klabjan, Diego, Mendiratta, Veena, Meng, Fanfei
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909169699782656
author Jang, Jaeyeon
Klabjan, Diego
Mendiratta, Veena
Meng, Fanfei
author_facet Jang, Jaeyeon
Klabjan, Diego
Mendiratta, Veena
Meng, Fanfei
contents Federated learning is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server. Most existing works have focused on horizontal or vertical data distributions, where each client possesses different samples with shared features, or each client fully shares only sample indices, respectively. However, the hybrid scheme is much less studied, even though it is much more common in the real world. Therefore, in this paper, we propose a generalized algorithm, FedGraph, that introduces a graph convolutional neural network to capture feature-sharing information while learning features from a subset of clients. We also develop a simple but effective clustering algorithm that aggregates features produced by the deep neural networks of each client while preserving data privacy.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09443
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network
Jang, Jaeyeon
Klabjan, Diego
Mendiratta, Veena
Meng, Fanfei
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated learning is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server. Most existing works have focused on horizontal or vertical data distributions, where each client possesses different samples with shared features, or each client fully shares only sample indices, respectively. However, the hybrid scheme is much less studied, even though it is much more common in the real world. Therefore, in this paper, we propose a generalized algorithm, FedGraph, that introduces a graph convolutional neural network to capture feature-sharing information while learning features from a subset of clients. We also develop a simple but effective clustering algorithm that aggregates features produced by the deep neural networks of each client while preserving data privacy.
title Hybrid FedGraph: An efficient hybrid federated learning algorithm using graph convolutional neural network
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2404.09443