.png){kind=icon}
Return
Federated domain generalization via data-centric flatness optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.113023.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Presents a data-centric method to find global flat minima in federated learning. • Generates surrogate global data through model-guided adversarial augmentation. • Theoretically upper-bounds robust risk, linking flatness to unseen-domain accuracy. • Outperforms earlier methods on several benchmarks.
Journal
IF:
7.6
Papers:
1.4W
Citations:
4.5W
Organization
.png){kind=icon}
