Encoding Robust Representation for Graph Generation

28 Sep 2018  ·  Dongmian Zou, Gilad Lerman ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction Citeseer (biased evaluation) SCAT (half of negative examples with 0 features) AUC 97.27 # 2
AP 97.57 # 2
Link Prediction Cora (biased evaluation) SCAT (half of negative examples with 0 features) AUC 94.48 # 2
AP 94.63 # 2
Link Prediction Pubmed (biased evaluation) SCAT (half of negative examples with 0 features) AUC 97.52 # 2
AP 97.19 # 2

Methods