2.1 Federated Learning 现有处理non-IID问题的方法分为提升本地训练效果和提升聚合效果,本文是前一种,因为对比损失函数在本地计算 其他研究方向有个性化联邦学习,尝试为每个客户端学习一个模型,本文属于经典联邦学习,学习单个全局最佳模型 2.2 Contrastive Learning 对比学习的核心原理是拉近相同样本的表征让模型学习到更好...
今天要介绍的就是其中一篇论文《Model-Contrastive Federated Learning》 一、Motivation 联邦学习的关键挑战是客户端之间数据的异质性(Non-IID),尽管已有很多方法(例如FedProx,SCAFFOLD)来解决这个问题,但是他们在图像数据集上的效果欠佳(见实验Table1)。 传统的对比学习是data-level的,本文改进了FedAvg的本地模型训练阶段...
model-contrastive federated learning 对比联邦学习(Contrastive Federated Learning)是基于联邦学习(Federated Learning)的一种机器学习技术,它受到了联合训练(Joint Training)的启发,通过在客户机训练数据集上进行联合训练,在客户机和服务器端应用搭配特征(Contrasting Features)以及对抗损失(Contrastive Loss)以提高模型的精度...
(Model-Contrastive Federated Learning)模型对比联邦学习 【摘要】 摘要 联邦学习使多方能够在不交流本地数据的情况下协作训练机器学习模型。 联邦学习的一个关键挑战是处理各方本地数据分布的异质性。 尽管已经提出了许多研究来应对这一挑战,但我们发现它们无法在具有深度学习模型......
we find that they fail to achieve high performance in image datasets with deep learning models. In this paper, we propose MOON: model-contrastive federated learning. MOON is a simple and effective federated learning framework. The key idea of MOON is to utilize the similarity between model repre...
This technique makes use of a complementary pairing of Model-Contrastive federated learning (MCFL) and Dynamic Hexagonal Grid Construction (DHGC). For reducing complexity, we propose a 3D constructed map using hybrid of Tweak Capsule Network (TCapsNet) and Graphical Convolutional Network (GCN). Our...
& Song, D. Model-contrastive federated learning. In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10713–10722 (2021). Benesty, J., Chen, J., Huang, Y. & Cohen, I. Pearson correlation coefficient. In Noise Reduction in Speech Processing. Springer ...
Li, Q., He, B. & Song, D. Model-contrastive federated learning. InProc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10713–10722 (2021). Benesty, J., Chen, J., Huang, Y. & Cohen, I. Pearson correlation coefficient. InNoise Reduction in Speech Proc...
Federated learning approaches for fuzzy cognitive maps to support clinical decision-making in dengue Eng. Appl. Artif. Intell., 153 (2023), Article 106371 View PDFView articleView in ScopusGoogle Scholar [44] Liu Z., Wu F., Wang Y., Pan X. FedCL: Federated contrastive learning for multi...
In this paper, we propose MOON: model-contrastive federated learning. MOON is a simple and effective federated learning framework. The key idea of MOON is to utilize the similarity between model representations to correct the local training of individual parties, i.e., conducting contrastive ...