Message Passing Neural Networks for Simplicial and Cell Complexes

Equivariant Subgraph Aggregation Networks (ICLR 2022 Spotlight)

GREAD: Graph Neural Reaction-Diffusion Networks, ICML 2023

Understanding and Extending Subgraph GNNs by Rethinking their Symmetries (NeurIPS 2022 Oral)

A Fortran-based feed-forward neural network library. Whilst this library currently has a focus on 3D convolutional neural networks (CNNs), it can handle most standard hidden layer forms of neural networks, with the plan to integrate more.

Message-Passing Monte Carlo (MPMC)

🐼PANDA: Expanded Width-Aware Message Passing Beyond Rewiring, ICML 2024

Official repository for On Over-Squashing in Message Passing Neural Networks (ICML 2023)

Measuring generalization properties of graph neural networks

Official repository for Self-Attention Message Passing for Contrastive Few-Shot Learning

Lorentz group equivariant autoencoders based on Lorentz Group Network

Implementation of message-passing neural net (MPNN)

A collection of projects using graph neural networks implemented from first principles, and using the PyTorch Geometric library

🧬 Official implementation of Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks [ICML 2024]

Graph Neural Network creation module, implemented in Tensorflow 2 with examples using the module and the iGNNition library for fast GNN prototyping.

Master thesis: JAT (Jraph Attention Networks), a deep learning architecture to predict the potential energy and forces of molecules. Adapts Graph Attention Networks (GATv2) within the Message Passing Neural Networks framework to computational chemistry in JAX

GNN trained on the ZINC dataset (graph-level regression)

Efficient Subgraph GNNs by Learning Effective Selection Policies (ICLR 2024)

Graph neural network autoencoders for jets in HEP

GGPM - GraphNN Generation of Organic Photovoltaic Molecules