CogDL Toolkit
CogDL: An extensive toolkit for deep learning on graphs
High Efficiency
CogDL utilizes well-optimized operators to speed up training and save GPU memory of GNN models.
Easy-to-Use
CogDL provides easy-to-use APIs for running experiments with the given models and datasets using hyper-parameter search.
Reproducibility
CogDL provides reproducible leaderboards for state-of-the-art models on most of important tasks in the graph domain.
MoE GCN
CogDL supports GNN models with Mixture of Experts (MoE). You can install FastMoE and try MoE GCN in CogDL now!
v0.3.0 Release
The new v0.3.0 release provides a fast spmm operator to speed up GNN training. We also release the first version of CogDL paper in arXiv. You can join our slack for discussion. πππ
v0.2.0 Release
The new v0.2.0 release includes easy-to-use experiment and pipeline APIs for all experiments and applications. The experiment API supports automl features of searching hyper-parameters. Thanks to all the contributors. π
OAGBert
CogDL provides OAGBert API for model inference (OAGBert is trained on large-scale academic corpus). Details of OAGBert usage can be found in this link.