Saved in:
Bibliographic Details
Main Authors: Pourpanah, Farhad, Molahasani, Mahdiyar, Soltany, Milad, Greenspan, Michael, Etemad, Ali
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916549105811456
author Pourpanah, Farhad
Molahasani, Mahdiyar
Soltany, Milad
Greenspan, Michael
Etemad, Ali
author_facet Pourpanah, Farhad
Molahasani, Mahdiyar
Soltany, Milad
Greenspan, Michael
Etemad, Ali
contents We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that aligning the gradients at both client and server levels can facilitate the generalization of the model to new (target) domains. Building on this insight, we propose a novel method named FedGaLA, which performs gradient alignment at the client level to encourage clients to learn domain-invariant features, as well as global gradient alignment at the server to obtain a more generalized aggregated model. To empirically evaluate our method, we perform various experiments on four commonly used multi-domain datasets, PACS, OfficeHome, DomainNet, and TerraInc. The results demonstrate the effectiveness of our method which outperforms comparable baselines. Ablation and sensitivity studies demonstrate the impact of different components and parameters in our approach. The source code is available at: https://github.com/MahdiyarMM/FedGaLA.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
Pourpanah, Farhad
Molahasani, Mahdiyar
Soltany, Milad
Greenspan, Michael
Etemad, Ali
Machine Learning
Artificial Intelligence
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that aligning the gradients at both client and server levels can facilitate the generalization of the model to new (target) domains. Building on this insight, we propose a novel method named FedGaLA, which performs gradient alignment at the client level to encourage clients to learn domain-invariant features, as well as global gradient alignment at the server to obtain a more generalized aggregated model. To empirically evaluate our method, we perform various experiments on four commonly used multi-domain datasets, PACS, OfficeHome, DomainNet, and TerraInc. The results demonstrate the effectiveness of our method which outperforms comparable baselines. Ablation and sensitivity studies demonstrate the impact of different components and parameters in our approach. The source code is available at: https://github.com/MahdiyarMM/FedGaLA.
title Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.16304