1 code implementation • 16 Sep 2021 • Seok-Ju Hahn, Minwoo Jeong, Junghye Lee
Due to the curse of statistical heterogeneity across clients, adopting a personalized federated learning method has become an essential choice for the successful deployment of federated learning-based services.
Ranked #1 on Personalized Federated Learning on MNIST (ACC@1-100Clients metric)
no code implementations • 29 Aug 2020 • Seok-Ju Hahn, Junghye Lee
Unlike conventional federated learning algorithms based on gradients, our framework does not require to disassemble a model (i. e., to linear components) or to perturb data (or encryption of data for aggregation) to preserve privacy.
no code implementations • 22 May 2020 • Yeongjae Gil, Xiaoqian Jiang, Miran Kim, Junghye Lee
Data integration and sharing maximally enhance the potential for novel and meaningful discoveries.
no code implementations • 18 Oct 2019 • Seok-Ju Hahn, Junghye Lee
PhysioNet2012, a dataset for prediction of mortality of patients in an Intensive Care Unit (ICU), was used to verify the performance of the proposed method.