High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.

Python package for graph neural networks in chemistry and biology

GraphGallery is a gallery for benchmarking Graph Neural Networks, From InplusLab.

Implementation of Principal Neighbourhood Aggregation for Graph Neural Networks in PyTorch, DGL and PyTorch Geometric

Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lightning, the Deep Graph Library, and PyTorch Geometric.

Source code for EMNLP 2020 paper: Double Graph Based Reasoning for Document-level Relation Extraction

Implementation of Directional Graph Networks in PyTorch and DGL

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on Deep Graph Library (DGL)

Reimplementation of Graph Autoencoder by Kipf & Welling with DGL.

NebulaGraph DGL(Deep Graph Library) Integration Package. (WIP)

2021MXAP-DGL rank2

MAXP 命题赛 任务一：基于DGL的图机器学习任务。队伍：Graph@ICT，🥉rank6。https://www.biendata.xyz/competition/maxp_dgl/

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

DGL implementation of EGES

Set of PyTorch modules for developing and evaluating different algorithms for embedding trees.

A DGL implementation of "Directional Message Passing for Molecular Graphs" (ICLR 2020).

A DGL implementation of "Graph Neural Networks with convolutional ARMA filters". (PAMI 2021)

DGL implementation of GNN-CCA: Graph Neural Networks for Cross-Camera Data Association [arXiv:2201.06311]