Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training

IEEE Internet of Things Journal; Vol. 12, Issue 13; pp: 23207-23221.

Đã lưu trong:

Chi tiết về thư mục
Những tác giả chính:	Tun, Ye Lin, Thwal, Chu Myaet, Nguyen, Huu Nhat Minh, Hong, Choong Seon
Định dạng:	Bài viết
Ngôn ngữ:	English
Được phát hành:	IEEE 2025
Những chủ đề:	Federated learning (FL) layer-wise multimodality progressive resource-efficient
Truy cập trực tuyến:	https://elib.vku.udn.vn/handle/123456789/5899
Các nhãn:	Thêm thẻ Không có thẻ, Là người đầu tiên thẻ bản ghi này!

Thư viện lưu trữ:	Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng

id	oai:elib.vku.udn.vn:123456789-5899
record_format	dspace
spelling	oai:elib.vku.udn.vn:123456789-58992025-11-18T01:58:56Z Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training Tun, Ye Lin Thwal, Chu Myaet Nguyen, Huu Nhat Minh Hong, Choong Seon Federated learning (FL) layer-wise multimodality progressive resource-efficient IEEE Internet of Things Journal; Vol. 12, Issue 13; pp: 23207-23221. Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate multimodal learning with privacy-preserving approaches like federated learning (FL). However, compared to conventional unimodal learning, multimodal setting requires dedicated encoders for each modality, resulting in larger and more complex models. Training these models requires significant resources, presenting a substantial challenge for FL clients operating with limited computation and communication resources. To address these challenges, we introduce LW-FedMML, a layer-wise federated multimodal learning (FedMML) approach which decomposes the training process into multiple stages. Each stage focuses on training only a portion of the model, thereby significantly reducing the memory and computational requirements. Moreover, FL clients only need to exchange the trained model portion with the central server, lowering the resulting communication cost. We conduct extensive experiments across various FL and multimodal learning settings to validate the effectiveness of our proposed method. The results demonstrate that LW-FedMML can compete with conventional end-to-end FedMML while significantly reducing the resource burden on FL clients. Specifically, LW-FedMML reduces memory usage by up to 2.7× , computational operations (FLOPs) by 2.4× , and total communication cost by 2.3× . We also explore a progressive training approach called Prog-FedMML. While it offers lesser resource efficiency than LW-FedMML, Prog-FedMML has the potential to surpass the performance of end-to-end FedMML, making it a viable option for scenarios with fewer resource constraints. 2025-11-18T01:58:44Z 2025-11-18T01:58:44Z 2025-07 Working Paper 2327-4662 10.1109/JIOT.2025.3554541 https://elib.vku.udn.vn/handle/123456789/5899 en application/pdf IEEE
institution	Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng
collection	DSpace
language	English
topic	Federated learning (FL) layer-wise multimodality progressive resource-efficient
spellingShingle	Federated learning (FL) layer-wise multimodality progressive resource-efficient Tun, Ye Lin Thwal, Chu Myaet Nguyen, Huu Nhat Minh Hong, Choong Seon Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
description	IEEE Internet of Things Journal; Vol. 12, Issue 13; pp: 23207-23221.
format	Working Paper
author	Tun, Ye Lin Thwal, Chu Myaet Nguyen, Huu Nhat Minh Hong, Choong Seon
author_facet	Tun, Ye Lin Thwal, Chu Myaet Nguyen, Huu Nhat Minh Hong, Choong Seon
author_sort	Tun, Ye Lin
title	Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
title_short	Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
title_full	Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
title_fullStr	Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
title_full_unstemmed	Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training
title_sort	resource-efficient federated multimodal learning via layer-wise and progressive training
publisher	IEEE
publishDate	2025
url	https://elib.vku.udn.vn/handle/123456789/5899
_version_	1849386808084791296

Resource-Efficient Federated Multimodal Learning via Layer-Wise and Progressive Training

Những quyển sách tương tự