TY - JOUR
T1 - Optimizing the Collaboration Structure in Cross-Silo Federated Learning
AU - Bao, Wenxuan
AU - Wang, Haohan
AU - Wu, Jun
AU - He, Jingrui
N1 - This work is supported by National Science Foundation under Award No. IIS-1947203, IIS-2117902, IIS-2137468, and Agriculture and Food Research Initiative (AFRI) grant no. 2020-67021-32799/project accession no.1024178 from the USDA National Institute of Food and Agriculture. The views and conclusions are those of the authors and should not be interpreted as representing the official policies of the funding agencies or the government.
PY - 2023
Y1 - 2023
N2 - In federated learning (FL), multiple clients collaborate to train machine learning models together while keeping their data decentralized. Through utilizing more training data, FL suffers from the potential negative transfer problem: the global FL model may even perform worse than the models trained with local data only. In this paper, we propose FEDCOLLAB, a novel FL framework that alleviates negative transfer by clustering clients into non-overlapping coalitions based on their distribution distances and data quantities. As a result, each client only collaborates with the clients having similar data distributions, and tends to collaborate with more clients when it has less data. We evaluate our framework with a variety of datasets, models, and types of non-IIDness. Our results demonstrate that FEDCOLLAB effectively mitigates negative transfer across a wide range of FL algorithms and consistently outperforms other clustered FL algorithms.
AB - In federated learning (FL), multiple clients collaborate to train machine learning models together while keeping their data decentralized. Through utilizing more training data, FL suffers from the potential negative transfer problem: the global FL model may even perform worse than the models trained with local data only. In this paper, we propose FEDCOLLAB, a novel FL framework that alleviates negative transfer by clustering clients into non-overlapping coalitions based on their distribution distances and data quantities. As a result, each client only collaborates with the clients having similar data distributions, and tends to collaborate with more clients when it has less data. We evaluate our framework with a variety of datasets, models, and types of non-IIDness. Our results demonstrate that FEDCOLLAB effectively mitigates negative transfer across a wide range of FL algorithms and consistently outperforms other clustered FL algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85168638720&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85168638720&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85168638720
SN - 2640-3498
VL - 202
SP - 1718
EP - 1736
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
T2 - 40th International Conference on Machine Learning, ICML 2023
Y2 - 23 July 2023 through 29 July 2023
ER -