DGL KE

Environment¶

on proj55:

kg-cu113-py39

conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
conda install -c dglteam dgl-cuda11.3

# dglke-0.1.2
pip install dglke

DGL-KE¶

python==3.8
dgl==0.4.3

DGLBACKEND=pytorch dglke_train --model_name TransE_l2 --dataset FB15k --batch_size 1000 \
--neg_sample_size 200 --hidden_dim 400 --gamma 19.9 --lr 0.25 --max_step 500 --log_interval 100 \
--batch_size_eval 16 -adv --regularization_coef 1.00E-09 --test --num_thread 1 --num_proc 8

KGReasoning¶

mkdir data
cd data
wget http://snap.stanford.edu/betae/KG_data.zip
unzip KG_data.zip