Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Tiandi, Liu, Wenyan, Yao, Kai, Li, Lichun, Su, Shangchao, Chen, Cen, Li, Xiang, Yin, Shan, Gao, Ming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915466063118336
author Ye, Tiandi
Liu, Wenyan
Yao, Kai
Li, Lichun
Su, Shangchao
Chen, Cen
Li, Xiang
Yin, Shan
Gao, Ming
author_facet Ye, Tiandi
Liu, Wenyan
Yao, Kai
Li, Lichun
Su, Shangchao
Chen, Cen
Li, Xiang
Yin, Shan
Gao, Ming
contents Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
Ye, Tiandi
Liu, Wenyan
Yao, Kai
Li, Lichun
Su, Shangchao
Chen, Cen
Li, Xiang
Yin, Shan
Gao, Ming
Machine Learning
Artificial Intelligence
Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained increasing attention for its ability to address data heterogeneity. However, most existing pFL methods assume that each client's data follows a single distribution and learn one client-level personalized model for each client. This assumption often fails in practice, where a single client may possess data from multiple sources or domains, resulting in significant intra-client heterogeneity and suboptimal performance. To tackle this challenge, we propose pFedBayesPT, a fine-grained instance-wise pFL framework based on visual prompt tuning. Specifically, we formulate instance-wise prompt generation from a Bayesian perspective and model the prompt posterior as an implicit distribution to capture diverse visual semantics. We derive a variational training objective under the semi-implicit variational inference framework. Extensive experiments on benchmark datasets demonstrate that pFedBayesPT consistently outperforms existing pFL methods under both feature and label heterogeneity settings.
title Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.19621