Graph Neural Network Library for PyTorch

A novel architecture and training strategy for graph neural networks (GNN). The proposed architecture, named as Autoencoder-Aided GNN (AA-GNN), compresses the convolutional features at multiple hidden layers, hinging on a novel end-to-end training procedure that learns different graph representations per each layer. As a result, the computationa…

Continuous regular group convolutions for Pytorch

Low-Level Graph Neural Network Operators for PyG

Python Framework built on PyTorch and PyTorch Geometric for working with Representation Learning on Graph Neural Networks.

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

Triangle mesh deep learning utility library.

Pytorch Implementation of Group-equivariant Convolutional Networks

[ICLR'24] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

Implementation of PocketGen: Generating Full-Atom Ligand-Binding Protein Pockets

A curated list of topological deep learning (TDL) resources and links.

TxGNN: Zero-shot prediction of therapeutic use with geometric deep learning and clinician centered design

Contextualizing protein representations using deep learning on protein networks and single-cell data

A library for differentiable robotics.

Code for our Nature Scientific Reports paper "A universal framework for accurate and efficient geometric deep learning of molecular systems"

Protein Graph Library

Package for the data-driven representation of non-linear dynamics over manifolds based on a statistical distribution of local phase portrait features. Includes specific example on dynamical systems, synthetic- and real neural datasets. https://agosztolai.github.io/MARBLE/

[ICML 2024] LSH-Based Efficient Point Transformer (HEPT)

Geometric deep learning of protein–DNA binding specificity

Spectral Framework For AI Model Evaluation