CS224W课程笔记第一章:绪论

 (一)课程大纲如下:

  1. Traditional methods: Graphlets, Graph Kernels
  2. Methods for node embeddings: DeepWalk, Node2Vec
  3. Graph Neural Networks: GCN, GraphSAGE, GAT, Theory of GNNs
  4. Knowledge graphs and reasoning: TransE, BetaE
  5. Deep generative models for graphs
  6. Applications to Biomedicine, Science, Industry 

(二)基本概念:

        表征学习representation learning:研究一种方法,来自动学习到数据的特征,直接应用于下游预测任务。 

        图的表征学习:将图的节点(或边、全图)表示为d维向量。(嵌入embedding)。图中接近的节点,在d维空间上也接近。


(三)图机器学习的任务:

  • Node classification: Predict a property of a node(节点级别)
  • Link prediction: Predict whether there are missing links between two nodes(边级别)
  • Graph classification: Categorize different graphs(图级别)
  • Clustering: Detect if nodes form a community(子图级别)
  • Other tasks:Graph generation,Graph evolution(图级别)

(四) 二部图

二部图的每一部都可以投影出一个图

CS224W课程笔记第一章:绪论_第1张图片

你可能感兴趣的:(CS224W课程笔记,人工智能,深度学习)