paper-with-me

Papers

GRAND: Graph Neural Diffusion

2021-06-21 · NeurIPS Workshop DLDE 2021 12 · Benjamin Paul Chamberlain, James Rowbottom, Maria Gorinova, Stefan Webb, Emanuele Rossi, Michael M. Bronstein

We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.

📄 PDF Abstract BibTeX arXiv:2106.10934

Code (1)

twitter-research/graph-neural-pde 공식 구현 pytorch

Tasks

Graph Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

GRAND++: Graph Neural Diffusion with A Source Term

2021-09-29 · ICLR 2022 4 · Matthew Thorpe, Tan Minh Nguyen, Hedi Xia, Thomas Strohmer 외

We propose GRAph Neural Diffusion with a source term (GRAND++) for graph deep learning with a limited number of labeled nodes, i.e., low-labeling rate. GRAND++ is a class of continuous-depth graph deep learning architect…

Deep LearningGraph Learning

PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturing

2026-03-16 · Benjamin Uhrich, Tim Häntschel, Erhard Rahm arxiv

A comprehensive understanding of heat transport is essential for optimizing various mechanical and engineering applications, including 3D printing. Recent advances in machine learning, combined with physics-based models,…

Transfer LearningGraph Learning

A charge-preserving method for solving graph neural diffusion networks

2023-12-16 · Lidia Aceto, Pietro Antonio Grassi

The aim of this paper is to give a systematic mathematical interpretation of the diffusion problem on which Graph Neural Networks (GNNs) models are based. The starting point of our approach is a dissipative functional le…

GRAND+: Scalable Graph Random Neural Networks

2022-03-12 · Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin 외

Graph neural networks (GNNs) have been widely adopted for semi-supervised learning on graphs. A recent study shows that the graph random neural network (GRAND) model can generate state-of-the-art performance for this pro…

Data AugmentationGraph LearningModel OptimizationNode Classification

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

2020-12-01 · NeurIPS 2020 12 · Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han 외

We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non…

Data AugmentationNode Classification