Window-based model averaging improves generalization in heterogeneous federated learning

A Silvi, A Rizzardi, D Caldarola, B Caputo… - IEEE …, 2024 - ieeexplore.ieee.org

Federated Learning (FL) allows training machine learning models in privacy-constrained
scenarios by enabling the cooperation of edge devices without requiring local data sharing …

被引用次数：2 相关文章所有 3 个版本

[PDF] arxiv.org

A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs

Y Sun, L Shen, D Tao - arXiv preprint arXiv:2409.18915, 2024 - arxiv.org

As a popular paradigm for juggling data privacy and collaborative training, federated
learning (FL) is flourishing to distributively process the large scale of heterogeneous …

When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather

G Rizzoli, M Caligiuri, D Shenaj, F Barbato… - arXiv preprint arXiv …, 2024 - arxiv.org

In Federated Learning (FL), multiple clients collaboratively train a global model without
sharing private data. In semantic segmentation, the Federated source Free Domain …

Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning

D Caldarola, P Cagnasso, B Caputo… - arXiv preprint arXiv …, 2024 - arxiv.org

Federated learning (FL) enables collaborative model training with privacy preservation. Data
heterogeneity across edge devices (clients) can cause models to converge to sharp minima …

BRAIN: Blockchain-based Inference and Training Platform for Large-Scale Models

S Park, J Lee, SM Moon - IEEE Access, 2024 - ieeexplore.ieee.org

As artificial intelligence (AI) is innovating various industries, there are concerns about the
trust and transparency of AI-driven inference and training results. To tackle these issues …

Fed3R: Recursive Ridge Regression for Federated Learning with strong pre-trained models

E Fanì, R Camoriano, B Caputo, M Ciccone - International Workshop on … - openreview.net

Current Federated Learning (FL) methods often struggle with high statistical heterogeneity
across clients' data, resulting in client drift due to biased local solutions. This issue is …