Skip to content

Latest commit

 

History

History

graph_knn

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

Weisfeiler-Lehman Kernel Network

This directory contains implementations of

These models are tested on Harvard Clean Energy Project, a molecule property prediction task.

Data

Data can be downloaded from https://drive.google.com/drive/folders/0B0GLTTNiVPEkdmlac2tDSzBFVzg?usp=sharing

We thank Hanjun Dai and Prof. Le Song for sharing this dataset.

Usage

All codes are tested on tensorflow 0.12.0, with CUDA 8.0.

Suppose you downloaded our code at $BASEDIR/graph_knn, please run the following command to add all modules in the pythonpath.

export PYTHONPATH=$BASEDIR/graph_knn

Training:

python nntrain --train $TRAIN_FILE --valid $VALIDATION_FILE --save_dir $MODEL_DIR

Testing:

python nntrain --test $TEST_FILE --model $MODEL_DIR