Saved in:
Bibliographic Details
Main Authors: He, Ningxin, Liu, Yang, Sun, Wei, Ye, Xiaozhou, Ouyang, Ye, Gao, Tiegang, Zhang, Zehui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.12254
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917011762708480
author He, Ningxin
Liu, Yang
Sun, Wei
Ye, Xiaozhou
Ouyang, Ye
Gao, Tiegang
Zhang, Zehui
author_facet He, Ningxin
Liu, Yang
Sun, Wei
Ye, Xiaozhou
Ouyang, Ye
Gao, Tiegang
Zhang, Zehui
contents Text-to-Image (T2I) models have demonstrated their versatility in a wide range of applications. However, adaptation of T2I models to specialized tasks is often limited by the availability of task-specific data due to privacy concerns. On the other hand, harnessing the power of rich multimodal data from modern mobile systems and IoT infrastructures presents a great opportunity. This paper introduces Federated Multi-modal Knowledge Transfer (FedMMKT), a novel framework that enables co-enhancement of a server T2I model and client task-specific models using decentralized multimodal data without compromising data privacy.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12254
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning
He, Ningxin
Liu, Yang
Sun, Wei
Ye, Xiaozhou
Ouyang, Ye
Gao, Tiegang
Zhang, Zehui
Machine Learning
Text-to-Image (T2I) models have demonstrated their versatility in a wide range of applications. However, adaptation of T2I models to specialized tasks is often limited by the availability of task-specific data due to privacy concerns. On the other hand, harnessing the power of rich multimodal data from modern mobile systems and IoT infrastructures presents a great opportunity. This paper introduces Federated Multi-modal Knowledge Transfer (FedMMKT), a novel framework that enables co-enhancement of a server T2I model and client task-specific models using decentralized multimodal data without compromising data privacy.
title FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2510.12254