← Search

Kuangpu Guo

2 accepted papers

2025

Cooperative Pseudo Labeling for Unsupervised Federated Classification

ICCV 2025poster

Unsupervised federated learning (UFL) aims to collaboratively train a global model across distributed clients without data sharing and label information. Previous UFL works have predominantly focused on representation learning and clustering tasks. Recently, vision language models (e.g., CLIP) have…

2025

Exploring Vacant Classes in Label-Skewed Federated Learning

AAAI 2025technical

Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques du…