SteinGen: Generating Fidelitous and Diverse Graph Samples
Generating graphs that preserve characteristic structures while promoting sample diversity can be challenging, especially when the number of graph observations is small. Here, we tackle the problem of graph generation from only one observed graph. The classical approach of graph generation from parametric models relies on the estimation of parameters, which can be inconsistent or expensive to compute due to intractable normalisation constants. Generative modelling based on machine learning techniques to generate high-quality graph samples avoids parameter estimation but usually requires abundant training samples. Our proposed generating procedure, SteinGen, which is phrased in the setting of graphs as realisations of exponential random graph models, combines ideas from Stein's method and MCMC by employing Markovian dynamics which are based on a Stein operator for the target model. SteinGen uses the Glauber dynamics associated with an estimated Stein operator to generate a sample, and re-estimates the Stein operator from the sample after every sampling step. We show that on a class of exponential random graph models this novel "estimation and re-estimation" generation strategy yields high distributional similarity (high fidelity) to the original data, combined with high sample diversity.
Code (1)
Tasks
DiversityGraph Generationparameter estimationSimilar Papers 제목 키워드 기반
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
We consider the task of generating diverse and novel videos from a single video sample. Recently, new hierarchical patch-GAN based approaches were proposed for generating diverse images, given only a single sample at tra…
DiversityVideo GenerationTopoVST: Toward Topology-fidelitous Vessel Skeleton Tracking
Automatic extraction of vessel skeletons is crucial for many clinical applications. However, achieving topologically faithful delineation of thin vessel skeletons remains highly challenging, primarily due to frequent dis…
Generative Expansion of Small Datasets: An Expansive Graph Approach
Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating …
Data AugmentationConditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation
Learning the underlying distribution of molecular graphs and generating high-fidelity samples is a fundamental research problem in drug discovery and material science. However, accurately modeling distribution and rapidl…
Drug DiscoveryGraph GenerationGraph SamplingMolecular Graph GenerationDiverse Rare Sample Generation with Pretrained GANs
Deep generative models are proficient in generating realistic data but struggle with producing rare samples in low density regions due to their scarcity of training datasets and the mode collapse problem. While recent me…
Density EstimationDiversity