返回
Fair Federated Learning with Multi-Objective Hyperparameter Optimization
DOI:10.1145/3676968.png)
摘要
En 中文
Federated learning (FL) is an attractive paradigm for privacy-aware distributed machine learning, which enables clients to collaboratively learn a global model without sharing clients' data. Recently, many strategies have been proposed to improve the generality of the global model and thus improve FL effect. However, existing strategies either ignore the fairness among clients or sacrifice performance for fairness. They cannot ensure that the gap among clients is as small as possible without sacrificing federated performance. To address this issue, we propose ParetoFed, , a new local information aggregation method dedicated to obtaining better federated performance with smaller gap among clients. Specifically, we propose to use multi-objective hyperparameter optimization (HPO) algorithm to gain global models that are both fair and effective. Then, we send Pareto Optimal global models to each client, allowing them to choose the most suitable one as the base to optimize their local model. ParetoFed not only make the global models more fair but also make the selection of local models more personalized, which can further improve the federated performance. Extensive experiments show that ParetoFed outperforms existing FL methods in terms of fairness, and even achieves better federated performance, which demonstrates the significance of our method.
Keyword:
Fair federated learning
hyperparameter optimization
multi-objective optimization
期刊
IF:
4.8
论文数:
1.3K
被引数:
4.4K
机构
引用论文
Weekly cisplatin and radical radiation therapy for advanced, recurrent, and poor prognosis cervical carcinoma
Cancer
IF0
Variation in Bluebunch Wheatgrass in Relation to Environment and Geographic Location蓝拟冰草在不同环境及地理区域的变异
Ecology
IF0
Contribution of the hindgut to digestion of diets in growing pigs and adult sows: effect of diet composition后肠对生长猪和成年母猪日粮消化的贡献: 日粮组成的影响

