Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

Local Superior Soups improves client training and pre-trained model adaptation in federated learning through regularized model interpolation.

Debiased Noise Editing on Foundation Models for Fair Medical Image Classification

DNE mitigates spurious correlations through noise editing for fairness-aware medical image processing with white-box and black-box foundation model APIs.

FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation

FedSoup uses selective model interpolation to balance local and global performance, reduce overfitting, and seek flat minima for improved generalization.