电子科技2026，Vol.39Issue(2)：9-18,10.DOI:10.16180/j.cnki.issn1007-7820.2026.02.002
基于伪标签的二阶段时序半监督学习框架
A Two-Stage Sequential Semi-Supervised Learning Framework Based on Contrast Learning
摘要
Abstract
In view of the problem of scarce labeled data in some scenarios of time series classification,this study proposes a two-stage time series semi-supervised learning framework based on pseudo-labels.In the first stage,contrastive learning is used for training to construct a base classification model and label the unlabeled data.In the second stage,appropriate pseudo-labeling techniques are employed to retrain the model,so as to make full use of the close association between labeled data and unlabeled data to improve the model performance.Experiments are conducted on multiple public time series classification datasets to verify the effectiveness of the proposed framework,and an in-depth discussion is carried out on the applicable conditions of different pseudo-label training methods in the second stage.The experimental results show that when the proportion of labeled data is only 1%and 5%,the proposed learning framework can increase the average accuracy by approximately 5.1%and 3.5%respectively on two base models and multiple datasets.This fully demonstrates that the proposed method can effectively solve the problem of semi-supervised time series classification.关键词
半监督分类/时序数据/学习框架/伪标签技术/二阶段训练/对比学习/预训练/模型微调Key words
semi-supervised classification/time-series data/learning framework/pseudo-label technique/two-stage training/contrastive learning/pre-training/model fine-tuning分类
信息技术与安全科学引用本文复制引用
PENG Hongxin,LUO Shuyun,LUO Zhiyi..基于伪标签的二阶段时序半监督学习框架[J].电子科技,2026,39(2):9-18,10.基金项目
浙江省自然科学基金(LQ22F020027) （LQ22F020027）
辽宁省自然科学基金(2022-KF-21-01)Natural Science Foundation of Zhejiang(LQ22F020027) （2022-KF-21-01）
Natural Science Foundation of Liaoning(2022-KF-21-01) （2022-KF-21-01）
