gnn-model

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

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

Source Code of NeurIPS21 and T-PAMI24 paper: Recognizing Vector Graphics without Rasterization

Reconstruct billions of particle trajectories with graph neural networks

Using to predict the highway traffic speed

2021MXAP-DGL rank2

The official implementation of Convergent Graph Solvers (CGS)

An implementation from scratch of major Graph Neural Network (GNN) architectures using Numpy

A GNN model for the prediction of pure component vapor pressures.

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

Learning to Count Isomorphisms with Graph Neural Networks

Pytorch implementation of ProtoAU for recommendation.

DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction

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

Explainable Vulnerability Detection in C/C++ Using Edge-Aware Graph Attention Networks

This repository contains the official implementation of the paper titled "Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network", which was presented in the 18th International Conference on Document Analysis and Recognition (ICDAR 2024).

Official implementation of "Graph structure prompt learning: A novel methodology to improve performance of graph neural networks" published by Applied Intelligence

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.

A comprehensive deep learning framework for phishing detection, utilizing Graph Neural Networks (GraphSAGE) to analyze interconnected web features. Features include temporal graph construction, causal learning for robust time-series analysis, and integrated noise injection testing to evaluate model resilience against data imperfections.