FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiaochen, Wang, Jiaqi, Xiao, Houping, Chen, Jinghui, Ma, Fenglong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910926854160384
author Wang, Xiaochen
Wang, Jiaqi
Xiao, Houping
Chen, Jinghui
Ma, Fenglong
author_facet Wang, Xiaochen
Wang, Jiaqi
Xiao, Houping
Chen, Jinghui
Ma, Fenglong
contents Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are highly task-specific and modality-reliant. In the medical domain, however, the development of comprehensive foundation models is constrained by limited access to diverse modalities and stringent privacy regulations. To address these constraints, this study introduces a novel knowledge injection approach, FedKIM, designed to scale the medical foundation model within a federated learning framework. FedKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model using a designed adaptive Multitask Multimodal Mixture Of Experts (M3OE) module. This method not only preserves privacy but also enhances the model's ability to handle complex medical tasks involving multiple modalities. Our extensive experiments across twelve tasks in seven modalities demonstrate the effectiveness of FedKIM in various settings, highlighting its potential to scale medical foundation models without direct access to sensitive data.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10276
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models
Wang, Xiaochen
Wang, Jiaqi
Xiao, Houping
Chen, Jinghui
Ma, Fenglong
Machine Learning
Artificial Intelligence
Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are highly task-specific and modality-reliant. In the medical domain, however, the development of comprehensive foundation models is constrained by limited access to diverse modalities and stringent privacy regulations. To address these constraints, this study introduces a novel knowledge injection approach, FedKIM, designed to scale the medical foundation model within a federated learning framework. FedKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model using a designed adaptive Multitask Multimodal Mixture Of Experts (M3OE) module. This method not only preserves privacy but also enhances the model's ability to handle complex medical tasks involving multiple modalities. Our extensive experiments across twelve tasks in seven modalities demonstrate the effectiveness of FedKIM in various settings, highlighting its potential to scale medical foundation models without direct access to sensitive data.
title FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.10276