Semi-supervised Learning on Graphs with Generative Adversarial Nets
工作的动机在不同聚类簇之间的density gap里生成假样本，让分类学到的分类函数在分辨真假的同时，阻碍了density gap中的天然连续性。
为了生成density gap中的样本，文章构造了一种特殊的生成器-判别器的博弈均衡状态。使得表示层的中心区域成为density gap。
We investigate how generative adversarial nets (GANs) can help semi-supervised learning on graphs. We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs. In GraphSGAN, generator and classifier networks play a novel competitive game. At equilibrium, generator generates fake samples in low-density areas between subgraphs. In order to discriminate fake samples from the real, classifier implicitly takes the density property of subgraph into consideration. An efficient adversarial learning algorithm has been developed to improve traditional normalized graph Laplacian regularization with a theoretical guarantee.
Experimental results on several different genres of datasets show that the proposed GraphSGAN significantly outperforms several state-of-the-art methods. GraphSGAN can be also trained using mini-batch, thus enjoys the scalability advantage.