计算机科学
联合学习
水准点(测量)
骨料(复合)
钥匙(锁)
一般化
组分(热力学)
人工智能
机器学习
数据挖掘
数学分析
物理
复合材料
热力学
计算机安全
数学
材料科学
地理
大地测量学
作者
Jianqing Zhang,Hua Ye,Hao Wang,Tao Song,Zhang Xue,Ruhui Ma,Haibing Guan
出处
期刊:Proceedings of the ... AAAI Conference on Artificial Intelligence
[Association for the Advancement of Artificial Intelligence (AAAI)]
日期:2023-06-26
卷期号:37 (9): 11237-11244
被引量:6
标识
DOI:10.1609/aaai.v37i9.26330
摘要
A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. The key component of FedALA is an Adaptive Local Aggregation (ALA) module, which can adaptively aggregate the downloaded global model and local model towards the local objective on each client to initialize the local model before training in each iteration. To evaluate the effectiveness of FedALA, we conduct extensive experiments with five benchmark datasets in computer vision and natural language processing domains. FedALA outperforms eleven state-of-the-art baselines by up to 3.27% in test accuracy. Furthermore, we also apply ALA module to other federated learning methods and achieve up to 24.19% improvement in test accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI