This repository contains the code and data for the paper “Stable Diffusion: A Scalable Algorithm for Learning with Graph Neural Networks” by X. Wang, Y. Sun, Z. Liu, and J. Tang. The paper proposes a novel algorithm that can efficiently train graph neural networks on large-scale graphs with millions of nodes and edges. The algorithm is based on a stable diffusion process that preserves the graph structure and node features. The code is written in Python and PyTorch, and the data is from the OGB-LSC dataset.
This repository contains the code and data for the paper “Stable Diffusion: A Scalable Algorithm for Learning with Graph Neural Networks” by X. Wang, Y. Sun, Z. Liu, and J. Tang. The paper proposes a novel algorithm that can efficiently train graph neural networks on large-scale graphs with millions of nodes and edges. The algorithm is based on a stable diffusion process that preserves the graph structure and node features. The code is written in Python and PyTorch, and the data is from the OGB-LSC dataset.