ScholarGate
助手
Machine learningDeep learning / NLP / CV

弱监督图神经网络

弱监督图神经网络（WS-GNN）是一种图深度学习方法，当只有嘈杂、不完整或间接获得的标签时，它能从图结构数据（节点、边及其属性）中学习。通过将 GNN 消息传递与噪声鲁棒的训练策略相结合，它将图学习扩展到了难以获得干净、完全标注图的现实场景。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

弱监督图神经网络
图卷积网络 (GCN)图神经网络标签传播半监督图神经网络弱监督卷积神经网络弱监督 Transformer

来源

  1. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR 2017). link ↗
  2. Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57–81. DOI: 10.1016/j.aiopen.2021.01.001 ↗

如何引用本页

ScholarGate. (2026, June 3). Weakly Supervised Graph Neural Network. ScholarGate. https://scholargate.app/zh/deep-learning/weakly-supervised-graph-neural-network

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Weakly supervised graph neural network (Weakly Supervised Graph Neural Network). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/weakly-supervised-graph-neural-network · 数据集： https://doi.org/10.5281/zenodo.20539026