SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

04/04/2022
by   Karolis Martinkus, et al.
0

We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct modeling of the global and local graph structure and helps to overcome the expressivity and mode collapse issues of one-shot graph generators. Our novel GAN, called SPECTRE, enables the one-shot generation of much larger graphs than previously possible with one-shot models. SPECTRE outperforms state-of-the-art deep autoregressive generators in terms of modeling fidelity, while also avoiding expensive sequential generation and dependence on node ordering. A case in point, in sizable synthetic and real-world graphs SPECTRE achieves a 4-to-170 fold improvement over the best competitor that does not overfit and is 23-to-30 times faster than autoregressive generators.

READ FULL TEXT
research
01/25/2023

Improving Graph Generation by Restricting Graph Bandwidth

Deep graph generative modeling has proven capable of learning the distri...
research
03/07/2022

AgraSSt: Approximate Graph Stein Statistics for Interpretable Assessment of Implicit Graph Generators

We propose and analyse a novel statistical procedure, coined AgraSSt, to...
research
04/03/2017

Towards a property graph generator for benchmarking

The use of synthetic graph generators is a common practice among graph-o...
research
06/28/2020

Scalable Deep Generative Modeling for Sparse Graphs

Learning graph generative models is a challenging task for deep learning...
research
01/22/2020

Graph Generators: State of the Art and Open Challenges

The abundance of interconnected data has fueled the design and implement...
research
06/01/2018

Learning Neural Random Fields with Inclusive Auxiliary Generators

In this paper we develop Neural Random Field learning with Inclusive-div...
research
05/24/2023

Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation

Conditional graph generation tasks involve training a model to generate ...

Please sign up or login with your details

Forgot password? Click here to reset