Journal
EXPERT SYSTEMS WITH APPLICATIONS
Volume 237, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.121390
Keywords
Federated learning; Statistical heterogeneity; Ensemble learning
Ask authors/readers for more resources
Federated learning is a joint training pattern that fully utilizes data information while protecting data privacy. To address the challenge of statistical heterogeneity, a novel solution called Federated Ensemble Learning (FedEL) is proposed, which trains a group of weak learners with diversity to construct a global model. FedEL improves performance in non-independent identical distribution scenarios and reduces storage and reasoning costs compared to traditional ensemble learning.
Federated learning (FL) is a joint training pattern that fully utilizes data information whereas protecting data privacy. A key challenge in FL is statistical heterogeneity, which arises on account of the heterogeneity of local data distributions among clients, leading to inconsistency in local optimization goals and ultimately reducing the performance of globally aggregated models. We propose the Federated Ensemble Learning (FedEL), which makes full use of the heterogeneity of data distribution among clients to train a group of weak learners with diversity to construct a global model, which is a novel solution to the non-independent identical distribution (non-IID) problem. Experiments demonstrate that the proposed FedEL can improve performance in non-IID data scenarios. Even under extreme statistical heterogeneity, the average accuracy of FedEL is 3.54% higher than the state-of-the-art FL method. Moreover, the proposed FedEL reduces model storage and reasoning costs compared with traditional ensemble learning. The proposed FedEL demonstrates good generalization ability in experiments across different datasets, including natural scene image datasets and medical image datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available