Knowledge graphs (KGs) are data structures that store information about different entities (nodes) and their relations (edges). A common approach of using KGs in various machine learning tasks is to compute knowledge graph embeddings. DGL-KE is a high performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings. The package is implemented on the top of Deep Graph Library (DGL) and developers can run DGL-KE on CPU machine, GPU machine, as well as clusters with a set of popular models, including TransE, TransR, RESCAL, DistMult, ComplEx, and RotatE.
Figure: DGL-KE Overall Architecture
Currently DGL-KE support three tasks:
- Training, trains KG embeddings using
dglke_train(single machine) ordglke_dist_train(distributed environment). - Evaluation, reads the pre-trained embeddings and evaluates the embeddings with a link prediction task on the test set using
dglke_eval. - Inference, reads the pre-trained embeddings and do the linkage score ranking inference tasks using
dglke_scoreor do the embedding similarity ranking inference tasks usingdglke_emb_sim.
To install the latest version of DGL-KE run:
sudo pip3 install dgl
sudo pip3 install dglke
Train a transE model on FB15k dataset by running the following command:
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
This command will download the FB15k dataset, train the transE model and save the trained embeddings into the file.
DGL-KE is designed for learning at scale. It introduces various novel optimizations that accelerate training on knowledge graphs with millions of nodes and billions of edges. Our benchmark on knowledge graphs consisting of over 86M nodes and 338M edges shows that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines (48 cores/machine). These results represent a 2×∼5× speedup over the best competing approaches.
Figure: DGL-KE vs GraphVite on FB15k
Figure: DGL-KE vs Pytorch-BigGraph on Freebase
Learn more details with our documentation! If you are interested in the optimizations in DGL-KE, please check out our paper for more details.
If you use DGL-KE in a scientific publication, we would appreciate citations to the following paper:
@misc{zheng2020dglke,
title={DGL-KE: Training Knowledge Graph Embeddings at Scale},
author={Da Zheng and Xiang Song and Chao Ma and Zeyuan Tan and Zihao Ye and Jin Dong and Hao Xiong and Zheng Zhang and George Karypis},
year={2020},
eprint={2004.08532},
archivePrefix={arXiv},
}
This project is licensed under the Apache-2.0 License.