Graph Generation via Scattering

  title={Graph Generation via Scattering},
  author={Dongmian Zou and 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, some of these methods are complex as well as difficult to train and fine-tune. 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… 
2 Citations

Figures and Tables from this paper

Fractional Wavelet-Based Generative Scattering Networks
A new dimensionality reduction method named feature-map fusion (FMF) is developed instead of performing PCA to better retain the information of FrScatNets, and the effect of image fusion on the quality of the generated image is discussed.
Geometric wavelet scattering on graphs and manifolds
The geometric wavelets scattering transform is an adaptation of the Euclidean wavelet scattering transform, first introduced by S. Mallat, to graph and manifold data and has several desirable properties.


Designing Random Graph Models Using Variational Autoencoders With Applications to Chemical Design
Experiments reveal that the proposed variational autoencoder for graphs is able to learn and mimic the generative process of several well-known random graph models and can be used to create new molecules more effectively than several state of the art methods.
GraphGAN: Graph Representation Learning with Generative Adversarial Nets
GraphGAN is proposed, an innovative graph representation learning framework unifying above two classes of methods, in which the generative model and discriminative model play a game-theoretical minimax game.
NetGAN: Generating Graphs via Random Walks
The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective, and is able to produce graphs that exhibit the well-known network patterns without explicitly specifying them in the model definition.
Generative networks as inverse problems with Scattering transforms
Deep convolutional network generators are computed by inverting a fixed embedding operator and demonstrating that they have similar properties as GANs or VAEs, without learning a discriminative network or an encoder.
Spectral Networks and Locally Connected Networks on Graphs
This paper considers possible generalizations of CNNs to signals defined on more general domains without the action of a translation group, and proposes two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian.
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
This work proposes to sidestep hurdles associated with linearization of discrete structures by having a decoder output a probabilistic fully-connected graph of a predefined maximum size directly at once by formulated as a variational autoencoder.
Deep Convolutional Networks on Graph-Structured Data
This paper develops an extension of Spectral Networks which incorporates a Graph Estimation procedure, that is test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
This work presents a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a
MolGAN: An implicit generative model for small molecular graphs
MolGAN is introduced, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuris-tics of previous likelihood-based methods.