Graph Neural Network Python Packages

egnn-pytorch

Implementation of E(n)-Equivariant Graph Neural Networks, in Pytorch

pgl

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

molcraft

A python package for building powerful molecular graph neural networks for chemistry and biology.

dive-into-graphs

A library for graph deep learning research

edge2torch

Build sparsely connected PyTorch neural networks from prior-knowledge graphs, with optional feature- and node-level attribution.

crslab

An Open-Source Toolkit for Building Conversational Recommender System(CRS)

dhl-mm

Sparse Lie algebra engine for G₂, F₄, E₆, E₇, E₈ — 913× compression, lattice gauge theory, equivariant GNN layers. pip install dhl-mm

chemicalx

A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)

solitairenet

Solitaire deep learning library

bigraph

Bipartite-network link prediction in Python

graphids

Graph-based intrusion detection using GCN, Transformer autoencoder, and contrastive learning

gigl

TODO

graphsite

Compute graph representations of protein binding sites