Shutong Chen

2 accepted papers

2026

FedMerge: Federated Model Merging for Personalization

Shutong Chen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

AAAI 2026technical

One global model in federated learning (FL) might not be sufficient to serve many clients with non-IID tasks and distributions. Despite recent advances in FL to train multiple global models for better personalization, they only provide limited model choices to clients, so local finetuning of multipl

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Personalized Additive Modeling for Multi-level Federated Learning

Shutong Chen, Tianyi Zhou, Guodong Long, Jie Ma, Jing Jiang, Chengqi Zhang

ICML 2026poster

Contemporary AI faces the challenge of balancing generality with user-specific personalization. In federated learning (FL), this challenge is amplified by highly heterogeneous client data with complex non-IID patterns beyond standard modeling assumptions. Many existing FL methods are designed for re…

Cited by 0 Source ↗Scholar ↗