@[TOC]GNN
Resources
从图(Graph)到图卷积(Graph Convolution):漫谈图神经网络模型 (一)
Vocabulary
- Fixed Point Theorem : a convergency guarantee
- Contraction Map
- BP: Almeida-Pineda vs BPTT
Short Notes
- To make f f f a Contraction Map: Penalize Jacobian Matrix of f f f over H H H. I.e. Bound its derivative.
- GNN: stop when converged.
- GNN drawbacks
- Edges serve only as connections not learned
- Not suitable for learning Graph Representation: all nodes share info with each other.
- GGNN: replace convergent f f f with a Gated Unit like in RNN. Use BPTT instead of AP and can output before convergence. Edges now have weights that can be updated.
Q&A
- From Tree to Graph: this is all?
- Spectual Domain vs Spatial Domain
- How to update weights
- Attention
本文深入探讨了图神经网络(GNN)的基本概念及其在图数据上的应用,对比了传统图卷积方法与GNN的区别,解析了GNN的不足及改进方案GGNN,强调了边权重的学习与更新在图表示学习中的重要性。
2193

被折叠的 条评论
为什么被折叠?



