COGDL TOOLKIT
  • Home
  • Documentation
  • Leaderboard
    • Node Classification
    • Link Prediction
    • Graph Classification
    • Heterogeneous Node Classification
    • Multiplex Link Prediction
  • Methods
  • Datasets
  • FAQ

CogDL: An Extensive Research Toolkit for
​Deep Learning on Graphs

KEG, Tsinghua University
中文版

What is CogDL?

CogDL is a graph representation learning toolkit that allows researchers and developers to easily train and compare baseline or custom models for node classification, link prediction and other tasks on graphs. It provides implementations of many popular models, including: non-GNN Baselines like Deepwalk, LINE, NetMF,  GNN Baselines like GCN, GAT, GraphSAGE.

Task-Oriented

CogDL focuses on tasks on graphs and provides corresponding models, datasets, and leaderboards.

Multiple Tasks

CogDL supports node classification and link prediction tasks on homogeneous / heterogeneous networks, as well as graph classification.

Easy-Running

CogDL supports running multiple experiments simultaneously on multiple models and datasets under a specific task using multiple GPUs.

Extensibility

You can easily add new datasets, models and tasks and conduct experiments for them!
Getting Started
View Leaderboard
Methods
Datasets
FAQ
github
poster
Create a free web site with Weebly
  • Home
  • Documentation
  • Leaderboard
    • Node Classification
    • Link Prediction
    • Graph Classification
    • Heterogeneous Node Classification
    • Multiplex Link Prediction
  • Methods
  • Datasets
  • FAQ