电子学报2024，Vol.52Issue(3)：885-897,13.DOI:10.12263/DZXB.20220037
基于元学习的图卷积网络少样本学习模型
Few-Shot Learning on Graph Convolutional Network Based on Meta learning
摘要
Abstract
Few shot learning is a hot and difficult problem in the field of machine learning.The existing few-shot learning model cannot effectively capture the relationships between data feature information and data label,thus causing the generalization ability of the resulting classifier would be weaker.A few-shot learning of graph convolutional network on prototype space,termed FSL-GCNPS,is developed.Firstly,the feature vectors are extracted on multi-task data by convolu-tional network.Secondly,in order to map the feature vectors into the prototype space,representation learning for the classes based on prototype network is proposed.Next,the graph is structured by combing the classes prototype vectors with class vectors.Then,FSL-GCNPS is trained using Meta learning.The experimental results show that FSL-GCNPS has better cross-domain adaptability in the medical image domain compared with the traditional deep learning models.Meanwhile,the FSL-GCNPS model has better classification accuracy and classification stability compared with the classical Few-shot learn-ing algorithm.关键词
元学习/图卷积网络/卷积神经网络/少样本学习/原型空间Key words
meta learning/graph convolutional network/convolutional neural network/few-shot learning/proto-type space分类
信息技术与安全科学引用本文复制引用
刘鑫磊,冯林,廖凌湘,龚勋,苏菡,王俊..基于元学习的图卷积网络少样本学习模型[J].电子学报,2024,52(3):885-897,13.基金项目
国家自然科学基金(No.61876158,No.71971151) （No.61876158,No.71971151）
四川省重点研发项目(No.23ZDYF1810) National Natural Science Foundation of China(No.61876158,No.71971151) （No.23ZDYF1810）
Key R&D Projects in Sichuan Province(No.23ZDYF1810) （No.23ZDYF1810）
