提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档
GNN综述 notes
《Deep graph similarity learning: a survey》
1】 The main distinction between GNNs and the traditional graph embedding is that :
- GNNs address graph-related tasks in an end-to-end manner, where the representation learning and the target learning task are conducted jointly. (Wu et al. 2020),
- while generally the graph embedding learns graph representations in an isolated stage and the learned representations are then used for the target task.
2】 deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space.
Therefore, the GNN deep models can better leverage the graph features for the specific learning task compared to the graph embedding methods.
