论文地址:Federated Learning with Non-IID Data 一、 Introduction 介绍 这部分内容先是介绍了FL的由来和发展,简单介绍了Fedavg算法(不了解的小伙伴需要看一下2016年谷歌那篇论文,流程比较简单),说明了一下FL通信的问题和研究,最后引出了FL的Non-IID问题,在一些特定的Non-IID数据集上Fedavg是可以收敛
《Achieving linear speedup with partial worker participation in non-iid federated learning》 这些方法与我们的方法是兼容的,可以很容易地集成到我们的方法中。 然而,Zhao等[32]的理论表明,参数偏差会累积,导致次优解。 Local Drift in Federated Learning fedavg的目标函数: (1)w∗=argminwL(w)=∑i=1N...
Federated Learning with Non-IID Data 论文笔记 /104632718 论文通过实验验证了,在non-IID数据中,使用FedAvg算法训练的模型会使准确率降低。 从图中可以看出在non-IID使用FedAvg算法训练的模型准确率有了明显的下降,但是对于IID...因为数据分布的不同。 FedAvg算法训练的模型准确率收到数据分布偏态性的影响。 研究...
Non-IID dataClient selectionDeep reinforcement learningKnowledge distillationFederated learning (FL) allows distributed client devices to jointly train an efficient global model without transmitting local data, thus providing effective privacy preservation. However, federated learning models trained on non ...
Federated Learning enables clients to train a joint model collaboratively without disclosing raw data. However, learning over non-IID data may raise performance degeneration, which has become a fundamental bottleneck. Despite numerous efforts to address this issue, challenges such as excessive local compu...
Non-IID Data Federated Learning with Non-IID Data IID: 独立同分布 (idependently and identically distributed, IID) 论文链接 Abstract 联合学习使资源受限的边缘计算设备(例如移动电话和IoT设备)能够学习共享的预测模型,同时将训练数据保持在本地。这种去中心化的训练模型方法提供了隐私,安全性,监管和经济利益。
Federated Learning with Non-IID Data IID:独立同分布 (idependently and identically distributed, IID) 论文链接 Abstract 联合学习使资源受限的边缘计算设备(例如移动电话和IoT设备)能够学习共享的预测模型,同时将训练数据保持在本地。这种去中心化的训练模型方法提供了隐私,安全性,监管和经济利益。在这项工作中,我们...
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with Non-IID data. arXiv abs/1806.00582 (2018) Google Scholar Zhu, H., Jin, Y.: Multi-objective evolutionary federated learning. IEEE Trans. Neural Netw. Learn. Syst.31(4), 1310–1322 (2020) ...
(2022). MSSA-FL: High-Performance Multi-stage Semi-asynchronous Federated Learning with Non-IID Data. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13369. Springer, ...
[CVPR2022]FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction AbstractFedDC的关键思想是利用这个学习到的局部漂移变量来弥补差距,即在参数水平上进行一致性。实验结果和分析表明,FedDC在各种图像分类任务上具有加速收敛性和更好的性能,在部分参与设… 炼丹门下炼...发表于联邦...