Information
title：
DANE: Domain Adaptive Network Embedding
authors：
Yizhou Zhang， Guojie Song， Lun Du， Shuwen Yang and Yilun Jin
Abstract
However, as previous methods usually focus on learning embeddings for a single network, they can not learn representations transferable on multiple networks. Hence, it is important to design a network embedding algorithm that supports downstream model transferring on different networks, known as domain adaptation. In this paper, we propose a novel Domain Adaptive Network Embedding framework, which applies graph convolutional network to learn transferable embeddings. In DANE, nodes from multiple networks are encoded to vectors via a shared set of learnable parameters so that the vectors share an aligned embedding space. The distribution of embeddings on different networks are further aligned by adversarial learning regularization. In addition, DANE’s advantage in learning transferable network embedding can be guaranteed theoretically.
Core Issue
能学得多个网络上的可迁移的表示
Methods
使用shared weight graph convolutional network 做 Embedding space Alignment，然后使用 GAN 做 Distribution Alignment
总体框架：
共享GCN的优化目标：
对抗学习正则:
Innovation
制定了设计一个域适应网络 embedding 框架的任务
Shortcomings
作者提出共享参数的GCN可以做Embedding space Alignment，不同网络相似局部结构的节点更close，这一点不是很明显，同时又没有实验支撑。
Others
迁移学习通常是为CV, NLP任务设计的模型，并不能直接用于Network Embedding，因为图要求具有旋转不变性，并且迁移学习的模型通常是supervised learning，而NE要求unsupervised learning.如果做特征上的迁移的话，就和其他数据上的迁移学习一样了，所有重点研究的应该是图的拓扑结构的迁移。
Think
- 使用注意力捕获节点之间的关系，该关系是可迁移的
为了令不同网络的具有相似结构的节点更close，可使用度来定义它们之间的相似性。 - 使用判别模型来捕捉可以迁移的图的结构模式