MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Luyuan, Lin, Manqing, Luan, Tianyu, Li, Cong, Fang, Yuejian, Shen, Qingni, Wu, Zhonghai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929339602305024
author Xie, Luyuan
Lin, Manqing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
author_facet Xie, Luyuan
Lin, Manqing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
contents Federated learning is widely used in medical applications for training global models without needing local data access. However, varying computational capabilities and network architectures (system heterogeneity), across clients pose significant challenges in effectively aggregating information from non-independently and identically distributed (non-IID) data. Current federated learning methods using knowledge distillation require public datasets, raising privacy and data collection issues. Additionally, these datasets require additional local computing and storage resources, which is a burden for medical institutions with limited hardware conditions. In this paper, we introduce a novel federated learning paradigm, named Model Heterogeneous personalized Federated Learning via Injection and Distillation (MH-pFLID). Our framework leverages a lightweight messenger model that carries concentrated information to collect the information from each client. We also develop a set of receiver and transmitter modules to receive and send information from the messenger model, so that the information could be injected and distilled with efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06822
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
Xie, Luyuan
Lin, Manqing
Luan, Tianyu
Li, Cong
Fang, Yuejian
Shen, Qingni
Wu, Zhonghai
Machine Learning
Artificial Intelligence
Federated learning is widely used in medical applications for training global models without needing local data access. However, varying computational capabilities and network architectures (system heterogeneity), across clients pose significant challenges in effectively aggregating information from non-independently and identically distributed (non-IID) data. Current federated learning methods using knowledge distillation require public datasets, raising privacy and data collection issues. Additionally, these datasets require additional local computing and storage resources, which is a burden for medical institutions with limited hardware conditions. In this paper, we introduce a novel federated learning paradigm, named Model Heterogeneous personalized Federated Learning via Injection and Distillation (MH-pFLID). Our framework leverages a lightweight messenger model that carries concentrated information to collect the information from each client. We also develop a set of receiver and transmitter modules to receive and send information from the messenger model, so that the information could be injected and distilled with efficiency.
title MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.06822