返回
An integrated framework for scalable and inductive graph-based semi-supervised learning with adaptive sample weighting
DOI:10.1016/j.engappai.2026.115696.png)
摘要
En 中文
• 介绍了一种可扩展的基于图的无监督学习算法。
• 将自适应样本加权概念扩展到大型数据集。
• 将标记样本的自适应权重引入无监督模型。
• 联合提供锚标签、锚图和线性映射。
• 使用三个大型数据集评估无监督分类效果。
Keyword:
Scalable graph-based semi-supervised learning
Adaptive weights
Reduced flexible manifold embedding
Anchor-to-anchor affinity graph
Inductive semi-supervised models
期刊
IF:
8
论文数:
5.7K
被引数:
3.5W
机构
引用论文
A semi-supervised learning algorithm via adaptive Laplacian graph一种基于自适应拉普拉斯图的半监督学习算法
NEUROCOMPUTING
IF6.5
Multiple-view flexible semi-supervised classification through consistent graph construction and label propagation
NEURAL NETWORKS
IF6.3
Deep semi-supervised learning via dynamic anchor graph embedding in latent space
NEURAL NETWORKS
IF6.3
A simple graph-based semi-supervised learning approach for imbalanced classification一种简单的基于图的半监督学习的不平衡分类方法
PATTERN RECOGNITION
IF7.6

