Saved in:
Bibliographic Details
Main Authors: Le, Huy Q., Tun, Ye Lin, Qiao, Yu, Nguyen, Minh N. H., Kim, Keon Oh, Huh, Eui-Nam, Hong, Choong Seon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.08521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915526449561600
author Le, Huy Q.
Tun, Ye Lin
Qiao, Yu
Nguyen, Minh N. H.
Kim, Keon Oh
Huh, Eui-Nam
Hong, Choong Seon
author_facet Le, Huy Q.
Tun, Ye Lin
Qiao, Yu
Nguyen, Minh N. H.
Kim, Keon Oh
Huh, Eui-Nam
Hong, Choong Seon
contents Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is popular in real-world scenarios. Prototype learning, which leverages the mean feature vectors within the same classes, has become a prominent solution for federated learning under domain shift. However, existing federated prototype learning methods focus soley on inter-domain prototypes and neglect intra-domain perspectives. In this work, we introduce a novel federated prototype learning method, namely I$^2$PFL, which incorporates $\textbf{I}$ntra-domain and $\textbf{I}$nter-domain $\textbf{P}$rototypes, to mitigate domain shift from both perspectives and learn a generalized global model across multiple domains in federated learning. To construct intra-domain prototypes, we propose feature alignment with MixUp-based augmented prototypes to capture the diversity within local domains and enhance the generalization of local features. Additionally, we introduce a reweighting mechanism for inter-domain prototypes to generate generalized prototypes that reduce domain shift while providing inter-domain knowledge across multiple clients. Extensive experiments on the Digits, Office-10, and PACS datasets illustrate the superior performance of our method compared to other baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08521
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
Le, Huy Q.
Tun, Ye Lin
Qiao, Yu
Nguyen, Minh N. H.
Kim, Keon Oh
Huh, Eui-Nam
Hong, Choong Seon
Machine Learning
Artificial Intelligence
Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is popular in real-world scenarios. Prototype learning, which leverages the mean feature vectors within the same classes, has become a prominent solution for federated learning under domain shift. However, existing federated prototype learning methods focus soley on inter-domain prototypes and neglect intra-domain perspectives. In this work, we introduce a novel federated prototype learning method, namely I$^2$PFL, which incorporates $\textbf{I}$ntra-domain and $\textbf{I}$nter-domain $\textbf{P}$rototypes, to mitigate domain shift from both perspectives and learn a generalized global model across multiple domains in federated learning. To construct intra-domain prototypes, we propose feature alignment with MixUp-based augmented prototypes to capture the diversity within local domains and enhance the generalization of local features. Additionally, we introduce a reweighting mechanism for inter-domain prototypes to generate generalized prototypes that reduce domain shift while providing inter-domain knowledge across multiple clients. Extensive experiments on the Digits, Office-10, and PACS datasets illustrate the superior performance of our method compared to other baselines.
title Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.08521