A Survey of Learning from Graphs with Heterophily

Code and Content for Manning Publication on Graph Neural Networks

A Graph Deep Learning Library for Music.

CFG based program similarity using Graph Neural Networks

with GUG, Let's explore the Graph Neural Network!

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

Awesome GNN Learning For beginners

Listing the research works related to risk control based on GNN and its interpretability. 1. we can learn the application of GNN in risk control (including fraud detection). 2. For possible prediction, we can use the interpretability of GNN to explaine how can we get such results.

This repository is a brief tutorial about how Graph convolutional networks and message passing networks work with example code demonstration using pytorch and torch_geometric

The repository is a collection of Jupyter notebooks showcasing various projects related to graph neural networks (GNNs). Each notebook provides a detailed explanation of the project and its implementation, making it easy for users to understand and replicate the results.

Originally the Intersectional Graph Project, SURRF (The Semantic Ubiquitous Relations Research Framework) is an AI-assisted, graph-based research engine, built with the perplexity.ai API and NextJS. SURRF enables researchers to navigate the web while creating knowledge graphs that users can save, organize, compile, and share.

Official PyTorch Implementation of paper 'Edge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction'

Implement GNN models (GAT, GCN)

This repository shows a use case of Graph ML for casinos in marketing: Market Segmentation . Skills: Azure SDK, azure datalake, node2vec, graphml, geometric pytorch, gnn

Graph Machine Learning Training Tutorial

Literature indexing using Graph Neural Networks and label-guided text embeddings.

Code for my Final Thesis for the Computer Engineering Degree: "Photon Energy Estimation with the Electromagnetic Calorimeter of the LHCb"

Developed a Graph Neural Network–based fraud detection system using PyTorch Geometric by modeling financial transactions as a graph, achieving high recall and ROC-AUC on a real-world Bitcoin transaction dataset.

SMILES converted into Graphs that contains atomic information, bonding informatics. Graphs considered as input for the NN to Predict Melting Pont of Liquid Crystals (LCs)

In this project I explore an potential approach to estimate a human’s intention in a dyadic collaborative manipulation task by learning to predict the intended future trajectory of the co-manipulated object via the latent graph representation of the system.

Stock return prediction project using baseline models, XGBoost, and Graph Neural Networks.

code & report files for Project of EE394V SPR 2021