Artificial Intelligence
图神经主动学习
Graph Neural Active LearningA machine learning paradigm that utilizes graph neural networks to iteratively select the most informative samples for labeling, thereby optimizing the performance of multi-label classification tasks with limited training data. / 一种机器学习范式，利用图神经网络迭代选择最具信息量的样本进行标注，从而在训练数据有限的情况下优化多标签分类任务的性能。
- Knowledge type
- 实际应用
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-11-03 22:05:39
Sub-knowledge points
Multi-Label Retinal Disease DiagnosisGraph Neural NetworksExpert Knowledge Integration
Higher-order knowledge points
Main parameters and performance indicators
Multi-Label Classification: The target task of diagnosing multiple retinal diseases simultaneouslyGraph Neural Network: The core model architecture for feature extraction and relationship modelingMulti-Expert Mechanism: Incorporates diverse expert knowledge to improve selection accuracy
Open problems
Scalability to very large-scale medical datasetsHandling class imbalance in rare retinal diseasesInterpretability of the active learning selection process
Related literature
ranked by community starsEnhancing Multi-Label retinal Disease diagnosis via Multi-Expert graph neural active learningOpen source
Related products and links
No item recorded yet
Creation and modification trail
1 recordsRecord title: Graph Neural Active Learning.
Node update feedback
review required