Code to run a novel recurrent-GNN model for weather prediction. Data: https://www.kaggle.com/PROPPG-PPG/hourly-weather-surface-brazil-southeast-region

The PyTorch 1.6 and Python 3.7 implementation for the paper Graph Convolutional Networks for Text Classification

GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction. In CIKM 2020.

Dense and Sparse Implementation of GAT written by PyTorch

The official implementation of Convergent Graph Solvers (CGS)

2021MXAP-DGL rank2

This paper explores the idea of using heterogeneous graph neural networks (Het-GNN) to partition old legacy monoliths into candidate microservices. We additionally take membership constraints that come from a subject matter expert who has deep domain knowledge of the application.

Clustering Hi-C contact map using graph neural networks. Utilities and data pipelines. Created as part of Bioinformatics institute spring 2022 project

Learning to Count Isomorphisms with Graph Neural Networks

HIV molecules classification using GNN with attention

deep learning model for interacting systems

Official code for [Neurips23] MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

Pytorch Geometric implementation of the "Gravity-Inspired Graph Autoencoders for Directed Link Prediction" paper.

CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)

GNN training in kubeflow.

An implementation from scratch of Graph Convolutional Networks (GCN) using Numpy

Inversion Symmetry-aware Directional PaiNN

This repository contains code implementations for Graph Neural Networks (GNNs). GNNs are a category of deep learning models tailored for tasks involving graph-structured data. The provided code enables users to explore and apply GNNs for tasks such as node classification, link prediction, and graph classification.

Using to predict the highway traffic speed