基于元学习的图卷积网络少样本学习模型

刘鑫磊; 冯林; 廖凌湘; 龚勋; 苏菡; 王俊

doi:10.12263/DZXB.20220037

您当前的位置：

首页 >

文章列表页 >

基于元学习的图卷积网络少样本学习模型

学术论文 | 更新时间：2025-12-11

- 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
- 电子学报 2024年52卷第3期页码：885-897
- 作者机构：
  
  1.四川师范大学计算机科学学院,四川成都 610100
  2.西南交通大学计算机与人工智能学院,四川成都 611730
  3.四川师范大学商学院,四川成都 610100
  4.资阳市公安局网络安全保卫支队,四川资阳 641399
- 作者简介：
  
  [ "刘鑫磊男，1994年出生于吉林省长春市．2022年毕业于四川师范大学计算机科学学院软件工程专业．现为四川省资阳市公安局网安支队民警. 主要研究方向为机器学习、少样本学习.E-mail: 1178101948@qq.com" ]
  [ "冯林男，1972年出生于四川省巴中市．现为四川师范大学计算机科学学院博士，教授，研究生导师．主要研究方向为机器学习、数据挖掘. E-mail: fenglin@sicnu.edu.cn" ]
  [ "廖凌湘男，1994年出生于福建省南平市.2022年毕业于四川师范大学计算机科学学院计算机科学与技术专业.现为四川航天职业技术学院硕士研究生、助教. E-mail: liao199411@163.com" ]
  龚勋男，1980年生.现为西南交通大学人工智能学院博士、教授、博士生导师.主要研究方向为人工智能、计算机视觉及图像处理. E-mail: xgong@swjtu.edu.cn
  苏菡女，1979年出生于四川省阿坝藏族自治州.现为四川师范大学计算机科学学院博士、教授、硕士生导师.主要研究方向为模式识别、图像处理. E-mail: suhan@sicnu.edu.cn
  王俊男，1984年生.现为四川师范大学商学院博士、副教授、硕士生导师.主要研究方向为复杂景区系统建模分析、不确定多属性决策理论与方法.E-mail: wangjun.sicnu@qq.com
- 基金信息：
  
  国家自然科学基金(61876158;71971151);四川省重点研发项目(23ZDYF1810)
- DOI：10.12263/DZXB.20220037
  中图分类号： TP181;
- 收稿：2022-01-03，
  
  修回：2022-12-21，
  
  纸质出版：2024-03-25
- 稿件说明：
移动端阅览
刘鑫磊,冯林,廖凌湘,等.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(03):885-897.

LIU Xin-lei, FENG Lin, LIAO Ling-xiang, et al.Few-Shot Learning on Graph Convolutional Network Based on Meta learning[J].Acta Electronica Sinica, 2024, 52(03): 885-897.
刘鑫磊,冯林,廖凌湘,等.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(03):885-897. DOI：10.12263/DZXB.20220037

LIU Xin-lei, FENG Lin, LIAO Ling-xiang, et al.Few-Shot Learning on Graph Convolutional Network Based on Meta learning[J].Acta Electronica Sinica, 2024, 52(03): 885-897. DOI：10.12263/DZXB.20220037

摘要

少样本学习是目前机器学习研究领域的热点和难点.针对现有的少样本学习模型不能有效捕捉数据特征与数据标签之间的联系，造成分类模型泛化能力弱的问题，提出一种基于元学习的原型空间图卷积网络少样本学习模型FSL-GCNPS（Few-Shot Learning of Graph Convolutional Network on Prototype Space）.首先，利用卷积神经网络提取多任务数据的特征向量；其次，为了将特征向量映射到原型空间中，根据元学习的训练策略得到特征向量的类原型表达；然后，通过类原型向量和类向量之间的嵌入表示，构建图结构数据，并进行图卷积网络训练、推理.实验结果表明，相较于经典少样本学习方法，FSL-GCNPS模型拥有更好的分类准确率和分类稳定性.同时，在医学图像领域数据集上实验表明，FSL-GCNPS具有很好的跨域适应性.

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 convolutional 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 learning algorithm.

关键词

Keywords

references

LECUN Y , BENGIO Y , HINTON G . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 .

李峰 , 詹邦成 , 辛蕾 , 等 . 基于新型联合感知矩阵的压缩学习目标识别技术 [J ] . 电子学报 , 2021 , 49 ( 11 ): 2108 - 2116 .

LI F , ZHAN B C , XIN L , et al . Target recognition technology based on a new joint sensing matrix for compressed learning [J ] . Acta Electronica Sinica , 2021 , 49 ( 11 ): 2108 - 2116 . (in Chinese)

史先进 , 曹爽 , 张重生 , 等 . 基于锚点的字符级甲骨图像自动标注算法研究 [J ] . 电子学报 , 2021 , 49 ( 10 ): 2020 - 2031 .

SHI X J , CAO S , ZHANG C S , et al . Research on automatic annotation algorithm for character-level oracle-bone images based on anchor points [J ] . Acta Electronica Sinica , 2021 , 49 ( 10 ): 2020 - 2031 . (in Chinese)

谢佳龙 , 张波涛 , 吕强 . 一种基于双流融合3D卷积神经网络的动态头势识别方法 [J ] . 电子学报 , 2021 , 49 ( 07 ): 1363 - 1369 .

XIE J L , ZHANG B T , LÜ Q . A dynamic head gesture recognition method based on 3D convolutional two-stream network fusion [J ] . Acta Electronica Sinica , 2021 , 49 ( 7 ): 1363 - 1369 . (in Chinese)

LI F F , ROBERT F , PIETRO P . A Bayesian approach to unsupervised one-shot learning of object categories [C ] // Proceedings of the Ninth IEEE International Conference on Computer Vision . Sydney : IEEE , 2003 : 1134 - 1141 .

余游 , 冯林 , 王格格 , 等 . 一种基于伪标签的半监督少样本学习模型 [J ] . 电子学报 , 2019 , 47 ( 11 ): 2284 - 2291 .

YU Y , FENG L , WANG G G , et al . A few-shot learning model based on semi-supervised with pseudo label [J ] . Acta Electronica Sinica , 2019 , 47 ( 11 ): 2284 - 2291 . (in Chinese)

代磊超 , 冯林 , 尚兴林 , 等 . 基于深度网络的快速少样本学习算法 [J ] . 模式识别与人工智能 , 2021 , 34 ( 10 ): 941 - 956 .

DAI L C , FENG L , SHANG X L , et al . Fast few-shot learning algorithm based on deep network [J ] . Pattern Recognition and Artificial Intelligence , 2021 , 34 ( 10 ): 941 - 956 . (in Chinese)

VINYALS O , BLUNDELL C , LILLICRAP T , et al . Matching networks for one shot learning [C ] // Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : ACM , 2016 : 3637 - 3645 .

SNELL J , SWERSKY K , ZEMEL R . Prototypical networks for few-shot learning [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach : ACM . 2017 : 4080 - 4090 .

SUNG F , YANG Y , ZHANG L , et al . Learning to compare: Relation network for few-shot learning [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Washington : IEEE , 2018 : 1199 - 1208 .

AMIT R , MEIR R . Meta-learning by adjusting priors based on extended PAC-Bayes theory [C ] // Proceedings of the 35th International Conference on Machine Learning . Stockholm : IEEE , 2018 : 205 - 214 .

FINN C , ABBEEL P , LEVINE S . Model-agnostic meta-learning for fast adaptation of deep networks [C ] // Proceedings of the 34th International Conference on Machine Learning . New York : ACM , 2017 : 1126 - 1135 .

ZHANG R , CHE T , GHAHRAMANI Z , et al . MetaGAN: An adversarial approach to few-shot learning [J ] . NeurIPS , 2018 , 2 ( 8 ): 1 .

ZHOU F , CAO C , ZHANG K , et al . Meta-GNN: On few-shot node classification in graph meta-learning [C ] // Proceedings of the 28th ACM International Conference on Information and Knowledge Management . New York : ACM , 2019 : 2357 - 2360 .

KIM J , KIM T , KIM S , et al . Edge-labeling graph neural network for few-shot learning [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 11 - 20 .

BRUNA J , ZAREMBA W , SZLAM A , et al . Spectral networks and deep locally connected networks on graphs [C ] // Proceedings of the 2nd International Conference on Learning Representations . Banff : ICLR , 2014 : 1 - 14 .

GILMER J , SCHOENHOLZ S S , RILEY P F , et al . Neural message passing for quantum chemistry [C ] // Proceedings of the 34th International Conference on Machine Learning . Sydney : ACM , 2017 : 1263 - 1272 .

AKELLA P N , CONNORS T J , KELLY J , et al . Creation and maintenance of social relationship network graphs : US7539697 [P ] . 2009-05-26 .

DEFFERRARD M , BRESSON X , VANDERGHEYNST P . Convolutional neural networks on graphs with fast localized spectral filtering [C ] // Proceedings of the 30th International Conference on Neural Information Processing Systems . New York : ACM , 2016 : 3844 - 3852 .

KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks [C ] // Proceedings of the 5th International Conference on Learning Representations . Toulon : ICLR , 2017 : 1 - 14 .

GARCIA V , BRUNA J . Few-shot learning with graph neural networks [C ] // Proceedings of the 6th International Conference on Learning Representations . Vancouver : ICLR , 2018 : 1 - 13 .

LI Q , HAN Z , WU X M . Deeper insights into graph convolutional networks for semi-supervised learning [C ] // Proceedings of the 32nd AAAI Conference on Artificial Intelligence . New Orleans : ACM , 2018 : 3538 - 3545 .

XU K , LI C , TIAN Y , et al . Representation learning on graphs with jumping knowledge networks [C ] // Proceedings of the 35th International Conference on Machine Learning . Stockholm : IEEE , 2018 : 5453 - 5462 .

YANG J , SHI R , NI B . Medmnist classification decathlon: A light- weight automl benchmark for medical image analysis [C ] // Proceedings of the 18th International Symposium on Biomedical Imaging . Nice : IEEE , 2021 : 191 - 195 .

GREGORY K , RICHARD , RUSLAN S . Siamese neural networks for one-shot image recognition [C ] // Proceedings of the International Conference on Machine Learning Deep Learning workshop . Lille : ICLR , 2015 : 1 - 30 .

ZHU X . Semi-supervised learning literature survey [J ] . World , 2005 , 10 : 1 - 38 .

CAMPANELLA G , HANNA M G , GENESLAW L , et al . Clinical-grade computational pathology using weakly supervised deep learning on whole slide images [J ] . Nature Medicine , 2019 , 25 ( 8 ): 1301 - 1309 .

NOORBAKHSH J , FARAHMAND S , NAMBURI S , et al . Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images [J ] . Nature Communications , 2020 , 11 ( 1 ): 1 - 14 .

KATHER J N , KRISAM J , CHAROENTONG P , et al . Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study [J ] . PLoS Medicine , 2019 , 16 ( 1 ): e1002730 .

HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern-Recognition . Las Vegas : IEEE , 2016 : 770 - 778 .

FEURER M , KLEIN A , EGGENSPERGER K , et al . Auto-sklearn: Efficient and robust automated machine learning [J ] . Automated Machine Learning , 2019 , 11 : 113 - 134 .

JIN H , SONG Q , HU X . Auto-keras: An efficient neural architecture search system [C ] // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . Anchorage : ACM , 2019 : 1946 - 1956 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于非一般类算子融合方法及硬件架构设计

共享超分的双分支遥感图像时空融合网络

基于局部表征少样本学习的高光谱图像跨场景分类

融合自注意力机制的多行为图对比学习推荐方法