Enterprise graph machine learning framework for billion-scale graphs for ML scientists and data scientists.

Engineer-To-Order (ETO) Graph Neural Scheduling (GNS) Project

A project which aims to abstract the analysis pipeline of a Particle Physics Analysis at ATLAS. This repository is a shared effort of University of Sydney, Duke and DESY.

Learning Fraud Detection from research papers and industry applications.

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

E(3)-equivariant graph neural networks (e3nn) for Julia

Explainable Neural Subgraph Matching with Graph Learnable Multi-hop Attention Networks

Implementing node similarity measures into pytorch geometric

Official reference implementation of our paper "Temporal Graph ODEs for Irregularly-Sampled Time Series" accepted at IJCAI 24

Official reference implementation of our paper "Long Range Propagation on Continuous-Time Dynamic Graphs" accepted at ICML24 and "Effective Non-Dissipative Propagation for Continuous-Time Dynamic Graphs" accepted at Temporal Graph Learning Workshop @ NeurIPS 2023

This is the python implementation of the Graph Neural Networks studied in arXiv:2409.02126 based on PyTorch and PyTorch Geometric.

Official repository for the paper "Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks"

GNN for spatiotemporal Forecasting using Extreme Value Theory

A novel and efficient methodology that enables the robot to maneuver safely through dense crowds in more ‘human-like’ patterns.

The official repository for the paper "Deep learning for dynamic graphs: models and benchmarks" accepted at IEEE TNNLS

This repository is the implementation of the paper Semi-Supervised Classification With Graph Convolutional Networks (aka GCN) by Kipf et al., ICLR 2017.

Scalable Expressiveness through Preprocessed Graph Perturbations (CIKM 2024)

Official code repository for the papers "Anti-Symmetric DGN: a stable architecture for Deep Graph Networks" accepted at ICLR 2023; "Non-Dissipative Propagation by Anti-Symmetric Deep Graph Networks"; and "Non-Dissipative Propagation by Randomized Anti-Symmetric Deep Graph Networks"

SREX-GNN improves Genetic Optimization Algorithms by enabling an Graph Neural Network to select the correct "genes" to cross-over