高技术通讯2024，Vol.34Issue(4)：342-355,14.DOI:10.3772/j.issn.1002-0470.2024.04.002
基于样本动态权重的课程式半监督学习方法
Curriculum paradigm based on the dynamic weights of samples for semi-supervised learning
摘要
Abstract
This work studies the difficulty of label propagation and serious noise interference in model training,which are due to the extreme lack of supervision signals in semi-supervised learning scenarios.Noise from pseudo-labeling and confirmation bias caused by low data utilization will lead to error accumulation along with the self-training process,thus forming irreversible deviation and damaging the performance.In this paper,a curriculum paradigm based on the dynamic weights of samples for semi-supervised learning is proposed,aiming at encouraging the model to utilize samples from easy to hard and gradually construct hyperplanes based on the non-discrete curriculum,so as to alleviate the generation of noise in the pseudo-labeling process and enhance the generalization ability of the mod-el.Specifically,from the intra-class perspective,prototypes of features are constructed by mixing pseudo-labels with high confidence,which can provide weak supervision signals.Then,the learning difficulties of samples are es-timated.From the inter-class perspective,label embedding is used to evaluate the semantic relevancy between cate-gories,and the discrimination between semantically related categories are weaken in the early stage of training.Comprehensive experiments and analyses are conducted on commonly-used semi-supervised learning benchmark datasets to demonstrate the effectiveness of this method.关键词
半监督学习/特征表示向量/课程学习/特征原型/语义相关度Key words
semi-supervised learning/feature representation vector/curriculum learning/prototype of fea-tures/semantic relevancy引用本文复制引用
朱徽,胡斌,宋怡宁,赵晓芳..基于样本动态权重的课程式半监督学习方法[J].高技术通讯,2024,34(4):342-355,14.基金项目
国家重点研发计划(2021YFF0703800)资助项目. （2021YFF0703800）
