Graph Neural Networks
Some well-explained blog articles on GNN and GCN.
Transformers are Graph Neural Networks
Reference: https://graphdeeplearning.github.io/post/transformers-are-gnns/
Through this post, I want to establish links between Graph Neural Networks (GNNs) and Transformers. I’ll talk about the intuitions behind model architectures in the NLP and GNN communities, make connections using equations and figures, and discuss how we could work together to drive progress.
从图(Graph)到图卷积(Graph Convolution)
Reference: https://www.cnblogs.com/SivilTaram/p/graph_neural_network_1.html
本文的提纲与叙述要点主要参考了2篇图神经网络的Survey,分别是来自IEEE Fellow的 A Comprehensive Survey on Graph Neural Networks 以及来自清华大学朱文武老师组的 Deep Learning on Graphs: A Survey, 在这里向两篇Survey的作者表示敬意。
Graph Attention Networks
Reference: https://petar-v.com/GAT/
A multitude of important real-world datasets come together with some form of graph structure: social networks, citation networks, protein-protein interactions, brain connectome data, etc. Extending neural networks to be able to properly deal with this kind of data is therefore a very important direction for machine learning research, but one that has received comparatively rather low levels of attention until very recently.