Skip to content

Latest commit

 

History

History
 
 

CompGCN

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 

README.md

CompGCN[ICLR 2020]

Paper: Composition- based Multi-Relational Graph Convolutional Networks

Code: https://github.com/malllabiisc/CompGCN

How to run

  • Clone the Openhgnn-DGL

    python main.py -m CompGCN -t node_classification -d aifb -g 0

    If you do not have gpu, set -gpu -1.

    Supported Dataset: RDFDataset

Performance: Node classification

Method AIFB MUTAG BGS AM
CompGCN(dgl) 91.66

TrainerFlow: [node classification flow](../../trainerflow/#Node classification flow)

Model

Hyper-parameter specific to the model

You can modify the parameters in openhgnn/config.ini

Description

hidden_dim
batch_size

Best config can be found in best_config

More

Contirbutor

Tianyu Zhao[GAMMA LAB]

If you have any questions,

Submit an issue or email to tyzhao@bupt.edu.cn.