FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Training

计算机科学 培训(气象学) 人工智能 机器学习 训练集 物理 气象学
作者
Yan Kang,Yang Liu,Xinle Liang
出处
期刊:ACM Transactions on Intelligent Systems and Technology [Association for Computing Machinery]
卷期号:13 (4): 1-16 被引量:30
标识
DOI:10.1145/3510031
摘要

Federated learning allows multiple parties to build machine learning models collaboratively without exposing data. In particular, vertical federated learning (VFL) enables participating parties to build a joint machine learning model based on distributed features of aligned samples. However, VFL requires all parties to share a sufficient amount of aligned samples. In reality, the set of aligned samples may be small, leaving the majority of the non-aligned data unused. In this article, we propose Federated Cross-view Training (FedCVT), a semi-supervised learning approach that improves the performance of the VFL model with limited aligned samples. More specifically, FedCVT estimates representations for missing features, predicts pseudo-labels for unlabeled samples to expand the training set, and trains three classifiers jointly based on different views of the expanded training set to improve the VFL model's performance. FedCVT does not require parties to share their original data and model parameters, thus preserving data privacy. We conduct experiments on NUS-WIDE, Vehicle, and CIFAR10 datasets. The experimental results demonstrate that FedCVT significantly outperforms vanilla VFL that only utilizes aligned samples. Finally, we perform ablation studies to investigate the contribution of each component of FedCVT to the performance of FedCVT. Code is available at https://github.com/yankang18/FedCVT
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
orixero应助wangjue采纳,获得10
刚刚
1秒前
liu完成签到,获得积分10
1秒前
Villanellel发布了新的文献求助50
2秒前
YJ888发布了新的文献求助10
2秒前
3秒前
HIT_C发布了新的文献求助30
5秒前
6秒前
7秒前
kkkkk完成签到,获得积分10
7秒前
三斤完成签到 ,获得积分20
7秒前
李茵发布了新的文献求助10
8秒前
8秒前
9秒前
9秒前
wyl发布了新的文献求助10
10秒前
11秒前
11秒前
小小小值钱完成签到,获得积分20
13秒前
wangjue发布了新的文献求助10
14秒前
15秒前
15秒前
木可发布了新的文献求助10
16秒前
16秒前
wyl完成签到,获得积分10
18秒前
汉堡包应助三斤采纳,获得10
19秒前
wangqiuhong发布了新的文献求助10
21秒前
22秒前
失眠的夜梦关注了科研通微信公众号
22秒前
今后应助HIT_C采纳,获得10
23秒前
今后应助SuperZzz采纳,获得10
24秒前
ZONG发布了新的文献求助10
26秒前
Nugget发布了新的文献求助10
27秒前
李茵完成签到,获得积分10
29秒前
量子星尘发布了新的文献求助10
29秒前
汉堡包应助风趣的老太采纳,获得10
30秒前
DongWei95发布了新的文献求助30
32秒前
32秒前
32秒前
猪猪hero发布了新的文献求助10
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174