paper-with-me

홈 › Papers

Adversarial Stein Training for Graph Energy Models

2020-09-21 · Anonymous

Learning distributions over graph-structured data is a challenging task. In this work we present an energy-based model (EBM) using graph neural networks (GNN) to learn permutation invariant unnormalized density functions on graphs. The model is trained via minimizing adversarial stein discrepancy. Samples from the model can be obtained via Langevin dynamics. We find that this approach achieves better results on graph generation compared to benchmark models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Generation

Similar Papers 제목 키워드 기반

Adversarial Stein Training for Graph Energy Models

2021-08-30 · Shiv Shankar

Learning distributions over graph-structured data is a challenging task with many applications in biology and chemistry. In this work we use an energy-based model (EBM) based on multi-channel graph neural networks (GNN) …

Graph Generation

Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics

2020-11-30 · Raghav Kansal, Javier Duarte, Breno Orzari, Thiago Tomei 외

We develop a graph generative adversarial network to generate sparse data sets like those produced at the CERN Large Hadron Collider (LHC). We demonstrate this approach by training on and generating sparse representation…

Generative Adversarial Network

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

2023-02-17 · Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the…

Dimensionality ReductionGeneralization Bounds

Wasserstein Adversarially Regularized Graph Autoencoder

2021-11-09 · Huidong Liang, Junbin Gao

This paper introduces Wasserstein Adversarially Regularized Graph Autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution via the…

ClusteringLink PredictionNode Clustering

Demystifying MMD GANs

2018-01-04 · ICLR 2018 1 · Mikołaj Bińkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton

We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias…