Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design

计算机科学 半监督学习 人工智能 机器学习 算法 数据挖掘
作者
Zhe Zhang,Shiyao Ma,Jiangtian Nie,Yi Wu,Yan Qiang,Xiao-Ke Xu,Dusit Niyato
标识
DOI:10.1109/hpcc-dss-smartcity-dependsys53884.2021.00047
摘要

Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the training data of local clients have ground-truth. Furthermore, FL faces the challenge of statistical heterogeneity, i.e., the distribution of the client's local training data is non-independent identically distributed (non-IID). In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL. In particular, this paper focuses on studying the labels-at-server scenario where there is only a limited amount of labeled data on the server and only unlabeled data on the clients. In our system design, we propose a novel method to tackle the problems, which we refer to as Federated Mixing (FedMix). FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models. To alleviate the non-IID problem, we propose a novel aggregation rule based on the frequency of the client's participation in training, namely the FedFreq aggregation algorithm, which can adjust the weight of the corresponding local model according to this frequency. Extensive evaluations conducted on CIFAR-10 dataset show that the performance of our proposed method is significantly better than those of the current baseline. It is worth noting that our system is robust to different non-IID levels of client data.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
小马甲应助典雅的三德采纳,获得10
刚刚
1秒前
慕青应助阔达的依秋采纳,获得10
1秒前
1秒前
1秒前
59完成签到 ,获得积分10
2秒前
2秒前
张小杰发布了新的文献求助10
2秒前
脑洞疼应助Mellow采纳,获得10
2秒前
在水一方应助阳光向秋采纳,获得10
2秒前
3秒前
3秒前
无风海发布了新的文献求助10
3秒前
田所浩二完成签到 ,获得积分10
3秒前
忠玉完成签到,获得积分10
4秒前
swy212应助康凯采纳,获得10
4秒前
拼搏的盼山完成签到 ,获得积分10
4秒前
张小小完成签到,获得积分10
4秒前
梦华发布了新的文献求助10
4秒前
5秒前
5秒前
zanzan发布了新的文献求助10
6秒前
小栗子完成签到,获得积分10
6秒前
麻雀发布了新的文献求助10
6秒前
古德赖可发布了新的文献求助10
7秒前
科研通AI5应助2804980075采纳,获得10
7秒前
好叭完成签到,获得积分20
7秒前
xc完成签到,获得积分10
7秒前
Liy完成签到,获得积分10
7秒前
sxc完成签到,获得积分10
7秒前
7秒前
cy4psych0完成签到,获得积分10
7秒前
Yolo发布了新的文献求助10
8秒前
核平铀善完成签到,获得积分10
8秒前
sb发布了新的文献求助10
8秒前
威武紫青完成签到,获得积分20
8秒前
顾子墨完成签到,获得积分10
8秒前
草莓声明发布了新的文献求助20
9秒前
Bambookiller应助吴世勋fans采纳,获得10
9秒前
9秒前
高分求助中
All the Birds of the World 4000
Production Logging: Theoretical and Interpretive Elements 3000
Les Mantodea de Guyane Insecta, Polyneoptera 2000
Machine Learning Methods in Geoscience 1000
Resilience of a Nation: A History of the Military in Rwanda 888
Essentials of Performance Analysis in Sport 500
Measure Mean Linear Intercept 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3729900
求助须知:如何正确求助?哪些是违规求助? 3274756
关于积分的说明 9988621
捐赠科研通 2990154
什么是DOI,文献DOI怎么找? 1640914
邀请新用户注册赠送积分活动 779488
科研通“疑难数据库(出版商)”最低求助积分说明 748235