Saved in:
Bibliographic Details
Main Authors: Wang, Penghao, Chen, Qian, Zhang, Teng, Zhang, Yingwei, Lu, Wang, Chen, Yiqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.10817
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908320234733568
author Wang, Penghao
Chen, Qian
Zhang, Teng
Zhang, Yingwei
Lu, Wang
Chen, Yiqiang
author_facet Wang, Penghao
Chen, Qian
Zhang, Teng
Zhang, Yingwei
Lu, Wang
Chen, Yiqiang
contents Federated Learning (FL) has emerged as an effective solution for multi-institutional collaborations without sharing patient data, offering a range of methods tailored for diverse applications. However, real-world medical datasets are often multimodal, and computational resources are limited, posing significant challenges for existing FL approaches. Recognizing these limitations, we developed the Federated Healthcare Benchmark(FHBench), a benchmark specifically designed from datasets derived from real-world healthcare applications. FHBench encompasses critical diagnostic tasks across domains such as the nervous, cardiovascular, and respiratory systems and general pathology, providing comprehensive support for multimodal healthcare evaluations and filling a significant gap in existing benchmarks. Building on FHBench, we introduced Efficient Personalized Federated Learning with Adaptive LoRA(EPFL), a personalized FL framework that demonstrates superior efficiency and effectiveness across various healthcare modalities. Our results highlight the robustness of FHBench as a benchmarking tool and the potential of EPFL as an innovative approach to advancing healthcare-focused FL, addressing key limitations of existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FHBench: Towards Efficient and Personalized Federated Learning for Multimodal Healthcare
Wang, Penghao
Chen, Qian
Zhang, Teng
Zhang, Yingwei
Lu, Wang
Chen, Yiqiang
Machine Learning
Artificial Intelligence
Federated Learning (FL) has emerged as an effective solution for multi-institutional collaborations without sharing patient data, offering a range of methods tailored for diverse applications. However, real-world medical datasets are often multimodal, and computational resources are limited, posing significant challenges for existing FL approaches. Recognizing these limitations, we developed the Federated Healthcare Benchmark(FHBench), a benchmark specifically designed from datasets derived from real-world healthcare applications. FHBench encompasses critical diagnostic tasks across domains such as the nervous, cardiovascular, and respiratory systems and general pathology, providing comprehensive support for multimodal healthcare evaluations and filling a significant gap in existing benchmarks. Building on FHBench, we introduced Efficient Personalized Federated Learning with Adaptive LoRA(EPFL), a personalized FL framework that demonstrates superior efficiency and effectiveness across various healthcare modalities. Our results highlight the robustness of FHBench as a benchmarking tool and the potential of EPFL as an innovative approach to advancing healthcare-focused FL, addressing key limitations of existing methods.
title FHBench: Towards Efficient and Personalized Federated Learning for Multimodal Healthcare
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.10817