Feb 1, 2023 · In this work, we propose an Autoregressive Graph Network~(AGN) that learns forward physics using a temporal inductive bias.
Here we address the above challenges and present Graph Recurrent Neural Networks (GraphRNN), a scalable framework for learning generative models of graphs.
In this paper, we present DeepNC, a novel method for inferring the missing parts of a network based on a deep generative model of graphs. Specifically, our ...
In this work, we introduce a novel graph generative model,. Computation Graph Transformer (CGT) that addresses the three requirements above for the benchmark ...
Missing: Completion | Show results with:Completion
To solve these issues, we propose a novel auto-regressive generative model that learns a joint distribution of the entities and relations of the KG without ...
In this paper, we propose an efficient auto-regressive graph generative model, called Graph Recurrent. Attention Network (GRAN), which overcomes the ...
Jul 21, 2024 · This work aims to design a method that is invariant to the ordering of different DFS trajectories when generating graphs using RNNs. With ...
Nov 26, 2024 · GRAN improves upon the scalability of autoregressive models by using graph neural networks with an attention mechanism to generate blocks of ...
Sep 27, 2024 · Graph generative models often face a critical trade-off between learning complex distributions and achieving fast generation speed.
Feb 1, 2023 · This paper proposes an autoregressive diffusion model (ARM) that leverages the absorbing discrete diffusion as the diffusion process on graphs.