Encoding robust representation for graph generation
Encoding robust representation for graph generation
复制标题
DOI：
10.1109/ijcnn.2019.8851705
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Dongmian Zou;Gilad Lerman
中科院分区：
文献类型：
--
作者：
Dongmian Zou;Gilad Lerman
生成网络可以从简单的噪声中生成有意义的信号，如图像和文本。近年来，基于GAN和VAE的图和图信号生成方法得到了发展。然而，这些方法的数学性质尚不清楚，训练好的生成模型也很困难。这项工作提出了一种图形生成模型，该模型使用了最近对马拉特散射变换的适应。所提出的模型自然由一个编码器和一个解码器组成。该编码器是一种高斯化的图形散射变换，对信号和图形处理具有较强的鲁棒性。解码器是一个简单的全连接网络，适合于特定的任务，如链路预测、图上信号生成和全图信号生成。我们提出的系统的训练是有效的，因为它只适用于解码器和硬件要求适中。数值结果表明，该系统在链路预测、图形和信号生成方面具有较好的性能。
Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However, the mathematical properties of these methods are unclear, and training good generative models is difficult. This work proposes a graph generation model that uses a recent adaptation of Mallat’s scattering transform to graphs. The proposed model is naturally composed of an encoder and a decoder. The encoder is a Gaussianized graph scattering transform, which is robust to signal and graph manipulation. The decoder is a simple fully connected network that is adapted to specific tasks, such as link prediction, signal generation on graphs and full graph and signal generation. The training of our proposed system is efficient since it is only applied to the decoder and the hardware requirements are moderate. Numerical results demonstrate state-of-the-art performance of the proposed system for both link prediction and graph and signal generation.