scholar.google.com › citations
Oct 3, 2018 · This work proposes a graph generation system based on scattering and demonstrates competitive performance as well as indicates better promise of the ...
Oct 12, 2021 · We propose a representation-first approach to molecular graph generation. We guide the latent representation of an autoencoder by capturing graph structure ...
Signal generation on graphs: In this task, the graph is fixed and the set of vertices and edges is known. The goal is to generate signals on the given graph.
Oct 12, 2021 · We guide the latent representation of an autoencoder by capturing graph structure information with the geometric scattering transform and apply ...
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 ...
Abstract: We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We further use it to form a ...
The scattering transform has a multilayer structure and uses wavelet filters to propagate signals. It can be viewed as a convolutional neural network where no ...
This work guides the latent representation of an autoencoder by capturing graph structure information with the geometric scattering transform and applies ...
This work proposes a graph generation model that uses a recent adaptation of Mallat's scattering transform to graphs. The proposed model is ...
• Experiment: Generate a graph by a Stochastic Block Model, randomly select two vertices and perform “graph surgery”, then record. Page 44. Robustness to ...