Knowledge graph embedding research has mainly focused on learning continuous representations of knowledge graphs towards the link prediction problem. Recently developed frameworks can be effectively applied in a wide range of research-related applications. Yet, using these frameworks in real-world applications becomes more challenging as the size of the knowledge graph grows.
We developed the DICE Embeddings framework (dicee) to compute embeddings for large-scale knowledge graphs in a hardware-agnostic manner. To achieve this goal, we rely on
- Pandas & Co. to use parallelism at preprocessing a large knowledge graph,
- PyTorch & Co. to learn knowledge graph embeddings via multi-CPUs, GPUs, TPUs or computing cluster, and
- Huggingface to ease the deployment of pre-trained models.
Why Pandas & Co. ? A large knowledge graph can be read and preprocessed (e.g. removing literals) by pandas, modin, or polars in parallel. Through polars, a knowledge graph having more than 1 billion triples can be read in parallel fashion. Importantly, using these frameworks allow us to perform all necessary computations on a single CPU as well as a cluster of computers.
Why PyTorch & Co. ? PyTorch is one of the most popular machine learning frameworks available at the time of writing. PytorchLightning facilitates scaling the training procedure of PyTorch without boilerplate. In our framework, we combine PyTorch & PytorchLightning. Users can choose the trainer class (e.g., DDP by Pytorch) to train large knowledge graph embedding models with billions of parameters. PytorchLightning allows us to use state-of-the-art model parallelism techniques (e.g. Fully Sharded Training, FairScale, or DeepSpeed) without extra effort. With our framework, practitioners can directly use PytorchLightning for model parallelism to train gigantic embedding models.
Why Hugging-face Gradio? Deploy a pre-trained embedding model without writing a single line of code.
For more please visit dice-embeddings!
Click me!
git clone https://github.com/dice-group/dice-embeddings.git
conda create -n dice python=3.9 --no-default-packages && conda activate dice
pip3 install -r requirements.txtor
pip install diceeTo test the Installation
wget https://files.dice-research.org/datasets/dice-embeddings/KGs.zip --no-check-certificate && unzip KGs.zip
pytest -p no:warnings -x # Runs >114 tests leading to > 15 mins
pytest -p no:warnings --lf # run only the last failed test
pytest -p no:warnings --ff # to run the failures first and then the rest of the tests.To see the software architecture, execute the following command
pyreverse dicee/ && dot -Tpng -x classes.dot -o dice_software.png && eog dice_software.png
# or
pyreverse dicee/trainer && dot -Tpng -x classes.dot -o trainer.png && eog trainer.png
To see available Models
- TransE, DistMult, ComplEx, ConEx, QMult, OMult, ConvO, ConvQ, Keci
- All 44 models available in https://github.com/pykeen/pykeen#models
For more, please refer to
examples.
To see a code snippet
To Train a KGE model (KECI) and evaluate it on the train, validation, and test sets of the UMLS benchmark dataset.
from dicee.executer import Execute
from dicee.config import Namespace
args = Namespace()
args.model = 'Keci'
args.scoring_technique = "AllvsAll"
args.path_dataset_folder = "KGs/UMLS/"
args.path_to_store_single_run="Keci_UMLS"
args.num_epochs = 100
args.embedding_dim = 32
reports = Execute(args).start()
# reports["Train"]["MRR"] =>0.97089
# reports["Test"]["MRR"] => 0.8197
# See the Keci_UMLS folder embeddings and all other fileswhere the data is in the following form
$ head -3 KGs/UMLS/train.txt
acquired_abnormality location_of experimental_model_of_disease
anatomical_abnormality manifestation_of physiologic_function
alga isa entityA KGE model can also be trained from the command line
python -m dicee.run --path_dataset_folder "KGs/UMLS" --model Keci --eval_model "train_val_test"Models can be easily trained in a single node multi-gpu setting
python -m dicee.run --accelerator "gpu" --strategy "ddp" --path_dataset_folder "KGs/UMLS" --model Keci --eval_model "train_val_test" Train a KGE model by providing the path of a single file and store all parameters under newly created directory
called KeciFamilyRun.
python -m dicee.run --path_single_kg "KGs/Family/train.txt" --model Keci --path_to_store_single_run KeciFamilyRunwhere the data is in the following form
$ head -3 KGs/Family/train.txt
_:1 <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://www.w3.org/2002/07/owl#Ontology> .
<http://www.benchmark.org/family#hasChild> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://www.w3.org/2002/07/owl#ObjectProperty> .
<http://www.benchmark.org/family#hasParent> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://www.w3.org/2002/07/owl#ObjectProperty> .Apart from n-triples or standard link prediction dataset formats, we support ["owl", "nt", "turtle", "rdf/xml", "n3"]*. Moreover, a KGE model can be also trained by providing an endpoint of a triple store.
python -m dicee.run --sparql_endpoint "http://localhost:3030/mutagenesis/" --model KeciFor more, please refer to examples.
To see a code snippet
# pip install dicee
# wget https://hobbitdata.informatik.uni-leipzig.de/KG/KGs.zip --no-check-certificate & unzip KGs.zip
from dicee.executer import Execute
from dicee.config import Namespace
from dicee.knowledge_graph_embeddings import KGE
from dicee import QueryGenerator
from dicee.static_funcs import evaluate
from dicee.static_funcs import load_pickle
from dicee.static_funcs import load_json
# (1) Train a KGE model
args = Namespace()
args.model = 'Keci'
args.optim = 'Adam'
args.scoring_technique = "AllvsAll"
args.path_single_kg = "KGs/Family/family-benchmark_rich_background.owl"
args.backend = "rdflib"
args.num_epochs = 200
args.batch_size = 1024
args.lr = 0.1
args.embedding_dim = 512
result = Execute(args).start()
# (2) Load the pre-trained model
pre_trained_kge = KGE(path=result['path_experiment_folder'])
# (3) Single-hop query answering
# Query: ?E : \exist E.hasSibling(E, F9M167)
# Question: Who are the siblings of F9M167?
# Answer: [F9M157, F9F141], as (F9M167, hasSibling, F9M157) and (F9M167, hasSibling, F9F141)
predictions = pre_trained_kge.answer_multi_hop_query(query_type="1p",
query=('http://www.benchmark.org/family#F9M167',
('http://www.benchmark.org/family#hasSibling',)),
tnorm="min", k=3)
top_entities = [topk_entity for topk_entity, query_score in predictions]
assert "http://www.benchmark.org/family#F9F141" in top_entities
assert "http://www.benchmark.org/family#F9M157" in top_entities
# (2) Two-hop query answering
# Query: ?D : \exist E.Married(D, E) \land hasSibling(E, F9M167)
# Question: To whom a sibling of F9M167 is married to?
# Answer: [F9F158, F9M142] as (F9M157 #married F9F158) and (F9F141 #married F9M142)
predictions = pre_trained_kge.answer_multi_hop_query(query_type="2p",
query=("http://www.benchmark.org/family#F9M167",
("http://www.benchmark.org/family#hasSibling",
"http://www.benchmark.org/family#married")),
tnorm="min", k=3)
top_entities = [topk_entity for topk_entity, query_score in predictions]
assert "http://www.benchmark.org/family#F9M142" in top_entities
assert "http://www.benchmark.org/family#F9F158" in top_entities
# (3) Three-hop query answering
# Query: ?T : \exist D.type(D,T) \land Married(D,E) \land hasSibling(E, F9M167)
# Question: What are the type of people who are married to a sibling of F9M167?
# (3) Answer: [Person, Male, Father] since F9M157 is [Brother Father Grandfather Male] and F9M142 is [Male Grandfather Father]
predictions = pre_trained_kge.answer_multi_hop_query(query_type="3p", query=("http://www.benchmark.org/family#F9M167",
(
"http://www.benchmark.org/family#hasSibling",
"http://www.benchmark.org/family#married",
"http://www.w3.org/1999/02/22-rdf-syntax-ns#type")),
tnorm="min", k=5)
top_entities = [topk_entity for topk_entity, query_score in predictions]
print(top_entities)
assert "http://www.benchmark.org/family#Person" in top_entities
assert "http://www.benchmark.org/family#Father" in top_entities
assert "http://www.benchmark.org/family#Male" in top_entitiesFor more, please refer to examples/multi_hop_query_answering.
To see a code snippet
from dicee import KGE
# (1) Train a knowledge graph embedding model..
# (2) Load a pretrained model
pre_trained_kge = KGE(path='..')
# (3) Predict missing links through head entity rankings
pre_trained_kge.predict_topk(h=[".."],r=[".."])
# (4) Predict missing links through relation rankings
pre_trained_kge.predict_topk(h=[".."],t=[".."])
# (5) Predict missing links through tail entity rankings
pre_trained_kge.predict_topk(r=[".."],t=[".."])To see a code snippet
Stay tune for Keci with >10B parameters on DBpedia!
# To download a pretrained ConEx on DBpedia 03-2022
mkdir ConEx && cd ConEx && wget -r -nd -np https://hobbitdata.informatik.uni-leipzig.de/KGE/DBpedia/ConEx/ && cd ..from dicee import KGE
# (1) Load a pretrained ConEx on DBpedia
pre_trained_kge = KGE(path='ConEx')
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/Ulm"]) # tensor([0.9309])
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/German_Empire"]) # tensor([0.9981])
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/Kingdom_of_Württemberg"]) # tensor([0.9994])
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/Germany"]) # tensor([0.9498])
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/France"]) # very low
pre_trained_kge.triple_score(h=["http://dbpedia.org/resource/Albert_Einstein"],r=["http://dbpedia.org/ontology/birthPlace"],t=["http://dbpedia.org/resource/Italy"]) # very lowPlease contact: caglar.demir@upb.de or caglardemir8@gmail.com , if you lack hardware resources to obtain embeddings of a specific knowledge Graph.
- DBpedia version: 06-2022 Embeddings:
- Models: ConEx, QMult
- YAGO3-10 ConEx embeddings
- FB15K-237 ConEx embeddings
- WN18RR ConEx embeddings
- For more please look at Hobbit Data
To see a single line of code
from dicee import KGE
KGE(path='...').deploy(share=True,top_k=10)To see the interface of the webservice
Details
To build the Docker image: ``` docker build -t dice-embeddings . ```To test the Docker image:
docker run --rm -v ~/.local/share/dicee/KGs:/dicee/KGs dice-embeddings ./main.py --model AConEx --embedding_dim 16
Currently, we are working on our manuscript describing our framework. If you really like our work and want to cite it now, feel free to chose one :)
# Keci
Accepted at ECML. Stay tuned for the manuscript!
# LitCQD (will be included soon)
Accepted at ECML. Stay tuned for the manuscript!
# DICE Embedding Framework
@article{demir2022hardware,
title={Hardware-agnostic computation for large-scale knowledge graph embeddings},
author={Demir, Caglar and Ngomo, Axel-Cyrille Ngonga},
journal={Software Impacts},
year={2022},
publisher={Elsevier}
}
# KronE
@inproceedings{demir2022kronecker,
title={Kronecker decomposition for knowledge graph embeddings},
author={Demir, Caglar and Lienen, Julian and Ngonga Ngomo, Axel-Cyrille},
booktitle={Proceedings of the 33rd ACM Conference on Hypertext and Social Media},
pages={1--10},
year={2022}
}
# QMult, OMult, ConvQ, ConvO
@InProceedings{pmlr-v157-demir21a,
title = {Convolutional Hypercomplex Embeddings for Link Prediction},
author = {Demir, Caglar and Moussallem, Diego and Heindorf, Stefan and Ngonga Ngomo, Axel-Cyrille},
booktitle = {Proceedings of The 13th Asian Conference on Machine Learning},
pages = {656--671},
year = {2021},
editor = {Balasubramanian, Vineeth N. and Tsang, Ivor},
volume = {157},
series = {Proceedings of Machine Learning Research},
month = {17--19 Nov},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v157/demir21a/demir21a.pdf},
url = {https://proceedings.mlr.press/v157/demir21a.html},
}
# ConEx
@inproceedings{demir2021convolutional,
title={Convolutional Complex Knowledge Graph Embeddings},
author={Caglar Demir and Axel-Cyrille Ngonga Ngomo},
booktitle={Eighteenth Extended Semantic Web Conference - Research Track},
year={2021},
url={https://openreview.net/forum?id=6T45-4TFqaX}}
# Shallom
@inproceedings{demir2021shallow,
title={A shallow neural model for relation prediction},
author={Demir, Caglar and Moussallem, Diego and Ngomo, Axel-Cyrille Ngonga},
booktitle={2021 IEEE 15th International Conference on Semantic Computing (ICSC)},
pages={179--182},
year={2021},
organization={IEEE}
For any questions or wishes, please contact: caglar.demir@upb.de or caglardemir8@gmail.com