CogDL-TensorFlow

CogDL-TensorFlow: The TensorFlow Implementation of CogDL. With Support from Professor Jie Tang.

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.

cogdl-overview

Getting Started

Requirements and Installation

  • TensorFlow version >= 2.0.0
  • Python version >= 3.6
pip install -e .

Usage

You can use python scripts/train.py --task example_task --dataset example_dataset --model example_method to run example_method on example_data and evaluate it via example_task.

GitHub