One-Shot Federated Learning based on Random Feature Extractor

Luyuan Yang, Shayan Shafaei, Yiming Liu, Naeem Shahabi Sani, Yu Cai, Jun Huan, Chao Lan
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:7737-7750, 2026.

Abstract

The transition from multi-rounds federated learning to one-shot federated learning (OFL) markedly alleviates communication burden and represents a major step toward realistic deployment. Most existing OFL approaches require clients to perform local training, imposing a substantial computational burden on client side, while others rely on pre-trained models. In this paper, we propose a novel one-shot federated learning framework based on random feature extractor (FedRFE). Unlike existing approaches, it does not require any local model training or pre-trained model, featuring superior resource efficiency. Through comprehensive experiments, we show FedRFE achieves competitive performance while being robust in challenging scenarios including data heterogeneity and client scalability. Our code is available at\url{https://github.com/luyuanxyang/FedRFE}

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-yang26a, title = {One-Shot Federated Learning based on Random Feature Extractor}, author = {Yang, Luyuan and Shafaei, Shayan and Liu, Yiming and Shahabi Sani, Naeem and Cai, Yu and Huan, Jun and Lan, Chao}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {7737--7750}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/yang26a/yang26a.pdf}, url = {https://proceedings.mlr.press/v337/yang26a.html}, abstract = {The transition from multi-rounds federated learning to one-shot federated learning (OFL) markedly alleviates communication burden and represents a major step toward realistic deployment. Most existing OFL approaches require clients to perform local training, imposing a substantial computational burden on client side, while others rely on pre-trained models. In this paper, we propose a novel one-shot federated learning framework based on random feature extractor (FedRFE). Unlike existing approaches, it does not require any local model training or pre-trained model, featuring superior resource efficiency. Through comprehensive experiments, we show FedRFE achieves competitive performance while being robust in challenging scenarios including data heterogeneity and client scalability. Our code is available at\url{https://github.com/luyuanxyang/FedRFE}} }
Endnote
%0 Conference Paper %T One-Shot Federated Learning based on Random Feature Extractor %A Luyuan Yang %A Shayan Shafaei %A Yiming Liu %A Naeem Shahabi Sani %A Yu Cai %A Jun Huan %A Chao Lan %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-yang26a %I PMLR %P 7737--7750 %U https://proceedings.mlr.press/v337/yang26a.html %V 337 %X The transition from multi-rounds federated learning to one-shot federated learning (OFL) markedly alleviates communication burden and represents a major step toward realistic deployment. Most existing OFL approaches require clients to perform local training, imposing a substantial computational burden on client side, while others rely on pre-trained models. In this paper, we propose a novel one-shot federated learning framework based on random feature extractor (FedRFE). Unlike existing approaches, it does not require any local model training or pre-trained model, featuring superior resource efficiency. Through comprehensive experiments, we show FedRFE achieves competitive performance while being robust in challenging scenarios including data heterogeneity and client scalability. Our code is available at\url{https://github.com/luyuanxyang/FedRFE}
APA
Yang, L., Shafaei, S., Liu, Y., Shahabi Sani, N., Cai, Y., Huan, J. & Lan, C.. (2026). One-Shot Federated Learning based on Random Feature Extractor. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:7737-7750 Available from https://proceedings.mlr.press/v337/yang26a.html.

Related Material