AAAI 2026technical0 citations

FedMerge: Federated Model Merging for Personalization

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

Abstract

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 multiple models is still indispensable. This paper proposes a novel ``FedMerge

BibTeX
@inproceedings{aaai2026_fedmergefederate,
  title = {FedMerge: Federated Model Merging for Personalization},
  author = {Shutong Chen and Tianyi Zhou and Guodong Long and Jing Jiang and Chengqi Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}