FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Sunny, Jangid, Nikita, Das, Shounak, Sethi, Amit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910998632333312
author Gupta, Sunny
Jangid, Nikita
Das, Shounak
Sethi, Amit
author_facet Gupta, Sunny
Jangid, Nikita
Das, Shounak
Sethi, Amit
contents Domain Generalization (DG) seeks to train models that perform reliably on unseen target domains without access to target data during training. While recent progress in smoothing the loss landscape has improved generalization, existing methods often falter under long-tailed class distributions and conflicting optimization objectives. We introduce FedTAIL, a federated domain generalization framework that explicitly addresses these challenges through sharpness-guided, gradient-aligned optimization. Our method incorporates a gradient coherence regularizer to mitigate conflicts between classification and adversarial objectives, leading to more stable convergence. To combat class imbalance, we perform class-wise sharpness minimization and propose a curvature-aware dynamic weighting scheme that adaptively emphasizes underrepresented tail classes. Furthermore, we enhance conditional distribution alignment by integrating sharpness-aware perturbations into entropy regularization, improving robustness under domain shift. FedTAIL unifies optimization harmonization, class-aware regularization, and conditional alignment into a scalable, federated-compatible framework. Extensive evaluations across standard domain generalization benchmarks demonstrate that FedTAIL achieves state-of-the-art performance, particularly in the presence of domain shifts and label imbalance, validating its effectiveness in both centralized and federated settings. Code: https://github.com/sunnyinAI/FedTail
format Preprint
id arxiv_https___arxiv_org_abs_2506_08518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching
Gupta, Sunny
Jangid, Nikita
Das, Shounak
Sethi, Amit
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
I.2.6; C.1.4; D.1.3; I.5.1; H.3.4; I.2.10; I.4.0; I.4.1; I.4.2; I.4.6; I.4.7; I.4.8; I.4.9; I.4.10; I.5.1; I.5.2; I.5.4; J.2; I.2.11; I.2.10
Domain Generalization (DG) seeks to train models that perform reliably on unseen target domains without access to target data during training. While recent progress in smoothing the loss landscape has improved generalization, existing methods often falter under long-tailed class distributions and conflicting optimization objectives. We introduce FedTAIL, a federated domain generalization framework that explicitly addresses these challenges through sharpness-guided, gradient-aligned optimization. Our method incorporates a gradient coherence regularizer to mitigate conflicts between classification and adversarial objectives, leading to more stable convergence. To combat class imbalance, we perform class-wise sharpness minimization and propose a curvature-aware dynamic weighting scheme that adaptively emphasizes underrepresented tail classes. Furthermore, we enhance conditional distribution alignment by integrating sharpness-aware perturbations into entropy regularization, improving robustness under domain shift. FedTAIL unifies optimization harmonization, class-aware regularization, and conditional alignment into a scalable, federated-compatible framework. Extensive evaluations across standard domain generalization benchmarks demonstrate that FedTAIL achieves state-of-the-art performance, particularly in the presence of domain shifts and label imbalance, validating its effectiveness in both centralized and federated settings. Code: https://github.com/sunnyinAI/FedTail
title FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
I.2.6; C.1.4; D.1.3; I.5.1; H.3.4; I.2.10; I.4.0; I.4.1; I.4.2; I.4.6; I.4.7; I.4.8; I.4.9; I.4.10; I.5.1; I.5.2; I.5.4; J.2; I.2.11; I.2.10
url https://arxiv.org/abs/2506.08518