一般讲的GCN跟图卷积,还有deep walk 什么的,一时糊涂了,记录下查询结果。
先写出相关算法
- Vertex embedding approaches: LLE, Laplacian Eigenmaps, Graph Factorization, GraRep, HOPE, DNGR, GCN, LINE
- Graph embedding approaches: Patchy-san, sub2vec (embed subgraphs), WL kernel andDeep WL kernels
其实看到这个相关算法,就可以看到GCN是Vertex embedding 中的一类算法。通常,大家所说的图卷积,图嵌入,其实是对图进行 Encoder,粒度还是在节点层面。
Graph Embedding Vs Vertex Embedding
-
Vertex embeddings: We encode each vertex (node) with its own vector representation. We would use this embedding when we want to perform visualization or prediction on the vertex level, e.g. visualization of vertices in the 2D plane, or p