Encoding Robust Representation for Graph Generation

TL;DR

This paper introduces a robust graph generation model utilizing a graph scattering transform, achieving state-of-the-art results in link prediction and graph signal generation with efficient training and moderate hardware needs.

Contribution

It presents a novel graph generation approach combining a Gaussianized scattering transform encoder with a simple decoder, enhancing robustness and training efficiency.

Findings

State-of-the-art performance in link prediction

Effective graph and signal generation capabilities

Robustness to graph and signal manipulation

Abstract

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.