FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning

Neural Networks; Volume 183, 107017

Zapisane w:

Opis bibliograficzny
Główni autorzy:	Le, Q. Huy, Nguyen, Huu Nhat Minh, Thwal, Chu Myaet, Qiao, Yu, Zhang, Chaoning, Hong, Choong Seon
Format:	Bài viết
Język:	English
Wydane:	Elsevier 2025
Hasła przedmiotowe:	Federated learning personal data decentralized machine learning FL approaches autoencoder
Dostęp online:	https://doi.org/10.1016/j.neunet.2024.107017 https://elib.vku.udn.vn/handle/123456789/5802
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!

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:123456789-5802
record_format	dspace
spelling	oai:elib.vku.udn.vn:123456789-58022025-11-13T09:54:28Z FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning Le, Q. Huy Nguyen, Huu Nhat Minh Thwal, Chu Myaet Qiao, Yu Zhang, Chaoning Hong, Choong Seon Federated learning personal data decentralized machine learning FL approaches autoencoder Neural Networks; Volume 183, 107017 Federated learning (FL) enables a decentralized machine learning paradigm for multiple clients to collaboratively train a generalized global model without sharing their private data. Most existing works have focused on designing FL systems for unimodal data, limiting their potential to exploit valuable multimodal data for future personalized applications. Moreover, the majority of FL approaches still rely on labeled data at the client side, which is often constrained by the inability of users to self-annotate their data in real-world applications. In light of these limitations, we propose a novel multimodal FL framework, namely FedMEKT, based on a semi-supervised learning approach to leverage representations from different modalities. To address the challenges of modality discrepancy and labeled data constraints in existing FL systems, our proposed FedMEKT framework comprises local multimodal autoencoder learning, generalized multimodal autoencoder construction, and generalized classifier learning. Bringing this concept into the proposed framework, we develop a distillation-based multimodal embedding knowledge transfer mechanism which allows the server and clients to exchange joint multimodal embedding knowledge extracted from a multimodal proxy dataset. Specifically, our FedMEKT iteratively updates the generalized global encoders with joint multimodal embedding knowledge from participating clients through upstream and downstream multimodal embedding knowledge transfer for local learning. Through extensive experiments on four multimodal datasets, we demonstrate that FedMEKT not only achieves superior global encoder performance in linear evaluation but also guarantees user privacy for personal data and model parameters while demanding less communication cost than other baselines. 2025-11-13T09:54:14Z 2025-11-13T09:54:14Z 2025-03 Working Paper https://doi.org/10.1016/j.neunet.2024.107017 https://elib.vku.udn.vn/handle/123456789/5802 en application/pdf Elsevier
institution	Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng
collection	DSpace
language	English
topic	Federated learning personal data decentralized machine learning FL approaches autoencoder
spellingShingle	Federated learning personal data decentralized machine learning FL approaches autoencoder Le, Q. Huy Nguyen, Huu Nhat Minh Thwal, Chu Myaet Qiao, Yu Zhang, Chaoning Hong, Choong Seon FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
description	Neural Networks; Volume 183, 107017
format	Working Paper
author	Le, Q. Huy Nguyen, Huu Nhat Minh Thwal, Chu Myaet Qiao, Yu Zhang, Chaoning Hong, Choong Seon
author_facet	Le, Q. Huy Nguyen, Huu Nhat Minh Thwal, Chu Myaet Qiao, Yu Zhang, Chaoning Hong, Choong Seon
author_sort	Le, Q. Huy
title	FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
title_short	FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
title_full	FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
title_fullStr	FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
title_full_unstemmed	FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning
title_sort	fedmekt: distillation-based embedding knowledge transfer for multimodal federated learning
publisher	Elsevier
publishDate	2025
url	https://doi.org/10.1016/j.neunet.2024.107017 https://elib.vku.udn.vn/handle/123456789/5802
_version_	1849386790955253760

FedMEKT: Distillation-based embedding knowledge transfer for multimodal federated learning

Podobne zapisy