pykeen 1.4.0

A package for training and evaluating multimodal knowledge graph embeddings

PyKEEN

PyKEEN (Python KnowlEdge EmbeddiNgs) is a Python package designed to train and evaluate knowledge graph embedding models (incorporating multi-modal information).

Installation • Quickstart • Datasets • Models • Support • Citation

Installation

The latest stable version of PyKEEN can be downloaded and installed from PyPI with:

$ pip install pykeen

The latest version of PyKEEN can be installed directly from the source on GitHub with:

pip install git+https://github.com/pykeen/pykeen.git

More information about installation (e.g., development mode, Windows installation, extras) can be found in the installation documentation.

Quickstart

This example shows how to train a model on a dataset and test on another dataset.

The fastest way to get up and running is to use the pipeline function. It provides a high-level entry into the extensible functionality of this package. The following example shows how to train and evaluate the TransE model on the Nations dataset. By default, the training loop uses the stochastic local closed world assumption (sLCWA) training approach and evaluates with rank-based evaluation.

from pykeen.pipeline import pipeline

result = pipeline(
    model='TransE',
    dataset='nations',
)

The results are returned in an instance of the PipelineResult dataclass that has attributes for the trained model, the training loop, the evaluation, and more. See the tutorials on understanding the evaluation and making novel link predictions.

PyKEEN is extensible such that:

• Each model has the same API, so anything from pykeen.models can be dropped in
• Each training loop has the same API, so pykeen.training.LCWATrainingLoop can be dropped in
• Triples factories can be generated by the user with from pykeen.triples.TriplesFactory

The full documentation can be found at https://pykeen.readthedocs.io.

Implementation

Below are the models, datasets, training modes, evaluators, and metrics implemented in pykeen.

Datasets (25)

The citation for each dataset corresponds to either the paper describing the dataset, the first paper published using the dataset with knowledge graph embedding models, or the URL for the dataset if neither of the first two are available.

Name	Documentation	Citation	Entities	Relations	Triples
Clinical Knowledge Graph	pykeen.datasets.CKG	Santos et al., 2020	7617419	11	26691525
CoDEx (large)	pykeen.datasets.CoDExLarge	Safavi et al., 2020	77951	69	612437
CoDEx (medium)	pykeen.datasets.CoDExMedium	Safavi et al., 2020	17050	51	206205
CoDEx (small)	pykeen.datasets.CoDExSmall	Safavi et al., 2020	2034	42	36543
ConceptNet	pykeen.datasets.ConceptNet	Speer et al., 2017	28370083	50	34074917
Countries	pykeen.datasets.Countries	ZhenfengLei/KGDatasets	271	2	1158
Commonsense Knowledge Graph	pykeen.datasets.CSKG	Ilievski et al., 2020	2087833	58	4598728
DB100K	pykeen.datasets.DB100K	Ding et al., 2018	99604	470	697479
DBpedia50	pykeen.datasets.DBpedia50	Shi et al., 2017	24624	351	34421
Drug Repositioning Knowledge Graph	pykeen.datasets.DRKG	gnn4dr/DRKG	97238	107	5874257
FB15k	pykeen.datasets.FB15k	Bordes et al., 2013	14951	1345	592213
FB15k-237	pykeen.datasets.FB15k237	Toutanova et al., 2015	14505	237	310079
Hetionet	pykeen.datasets.Hetionet	Himmelstein et al., 2017	45158	24	2250197
Kinships	pykeen.datasets.Kinships	ZhenfengLei/KGDatasets	104	25	10686
Nations	pykeen.datasets.Nations	ZhenfengLei/KGDatasets	14	55	1992
OGB BioKG	pykeen.datasets.OGBBioKG	Hu et al., 2020	45085	51	5088433
OGB WikiKG	pykeen.datasets.OGBWikiKG	Hu et al., 2020	2500604	535	17137181
OpenBioLink	pykeen.datasets.OpenBioLink	Breit et al., 2020	180992	28	4563407
OpenBioLink (F1)	pykeen.datasets.OpenBioLinkF1	PyKEEN/pykeen-openbiolink-benchmark	116425	19	1716703
OpenBioLink (F2)	pykeen.datasets.OpenBioLinkF2	PyKEEN/pykeen-openbiolink-benchmark	110628	17	734925
OpenBioLink	pykeen.datasets.OpenBioLinkLQ	Breit et al., 2020	480876	32	27320889
Unified Medical Language System	pykeen.datasets.UMLS	ZhenfengLei/KGDatasets	135	46	6529
WordNet-18	pykeen.datasets.WN18	Bordes et al., 2014	40943	18	151442
WordNet-18 (RR)	pykeen.datasets.WN18RR	Toutanova et al., 2015	40559	11	92583
YAGO3-10	pykeen.datasets.YAGO310	Mahdisoltani et al., 2015	123143	37	1089000

Models (25)

Name	Reference	Citation
ComplEx	pykeen.models.ComplEx	Trouillon et al., 2016
ComplExLiteral	pykeen.models.ComplExLiteral	Kristiadi et al., 2018
ConvE	pykeen.models.ConvE	Dettmers et al., 2018
ConvKB	pykeen.models.ConvKB	Nguyen et al., 2018
DistMult	pykeen.models.DistMult	Yang et al., 2014
DistMultLiteral	pykeen.models.DistMultLiteral	Kristiadi et al., 2018
ERMLP	pykeen.models.ERMLP	Dong et al., 2014
ERMLPE	pykeen.models.ERMLPE	Sharifzadeh et al., 2019
HolE	pykeen.models.HolE	Nickel et al., 2016
KG2E	pykeen.models.KG2E	He et al., 2015
MuRE	pykeen.models.MuRE	Balažević et al., 2019
NTN	pykeen.models.NTN	Socher et al., 2013
PairRE	pykeen.models.PairRE	Chao et al., 2020
ProjE	pykeen.models.ProjE	Shi et al., 2017
RESCAL	pykeen.models.RESCAL	Nickel et al., 2011
RGCN	pykeen.models.RGCN	Schlichtkrull et al., 2018
RotatE	pykeen.models.RotatE	Sun et al., 2019
SimplE	pykeen.models.SimplE	Kazemi et al., 2018
StructuredEmbedding	pykeen.models.StructuredEmbedding	Bordes et al., 2011
TransD	pykeen.models.TransD	Ji et al., 2015
TransE	pykeen.models.TransE	Bordes et al., 2013
TransH	pykeen.models.TransH	Wang et al., 2014
TransR	pykeen.models.TransR	Lin et al., 2015
TuckER	pykeen.models.TuckER	Balažević et al., 2019
UnstructuredModel	pykeen.models.UnstructuredModel	Bordes et al., 2014

Losses (7)

Name	Reference	Description
bceaftersigmoid	pykeen.losses.BCEAfterSigmoidLoss	A module for the numerically unstable version of explicit Sigmoid + BCE loss.
bcewithlogits	pykeen.losses.BCEWithLogitsLoss	A module for the binary cross entropy loss.
crossentropy	pykeen.losses.CrossEntropyLoss	A module for the cross entopy loss that evaluates the cross entropy after softmax output.
marginranking	pykeen.losses.MarginRankingLoss	A module for the margin ranking loss.
mse	pykeen.losses.MSELoss	A module for the mean square error loss.
nssa	pykeen.losses.NSSALoss	An implementation of the self-adversarial negative sampling loss function proposed by [sun2019]_.
softplus	pykeen.losses.SoftplusLoss	A module for the softplus loss.

Regularizers (5)

Name	Reference	Description
combined	pykeen.regularizers.CombinedRegularizer	A convex combination of regularizers.
lp	pykeen.regularizers.LpRegularizer	A simple L_p norm based regularizer.
no	pykeen.regularizers.NoRegularizer	A regularizer which does not perform any regularization.
powersum	pykeen.regularizers.PowerSumRegularizer	A simple x^p based regularizer.
transh	pykeen.regularizers.TransHRegularizer	A regularizer for the soft constraints in TransH.

Optimizers (6)

Name	Reference	Description
adadelta	torch.optim.Adadelta	Implements Adadelta algorithm.
adagrad	torch.optim.Adagrad	Implements Adagrad algorithm.
adam	torch.optim.Adam	Implements Adam algorithm.
adamax	torch.optim.Adamax	Implements Adamax algorithm (a variant of Adam based on infinity norm).
adamw	torch.optim.AdamW	Implements AdamW algorithm.
sgd	torch.optim.SGD	Implements stochastic gradient descent (optionally with momentum).

Training Loops (2)

Name	Reference	Description
lcwa	pykeen.training.LCWATrainingLoop	A training loop that uses the local closed world assumption training approach.
slcwa	pykeen.training.SLCWATrainingLoop	A training loop that uses the stochastic local closed world assumption training approach.

Negative Samplers (2)

Name	Reference	Description
basic	pykeen.sampling.BasicNegativeSampler	A basic negative sampler.
bernoulli	pykeen.sampling.BernoulliNegativeSampler	An implementation of the Bernoulli negative sampling approach proposed by [wang2014]_.

Stoppers (2)

Name	Reference	Description
early	pykeen.stoppers.EarlyStopper	A harness for early stopping.
nop	pykeen.stoppers.NopStopper	A stopper that does nothing.

Evaluators (2)

Name	Reference	Description
rankbased	pykeen.evaluation.RankBasedEvaluator	A rank-based evaluator for KGE models.
sklearn	pykeen.evaluation.SklearnEvaluator	An evaluator that uses a Scikit-learn metric.

Metrics (6)

Metric	Description	Evaluator	Reference
Adjusted Mean Rank	The mean over all chance-adjusted ranks: mean_i (2r_i / (num_entities+1)). Lower is better.	rankbased	pykeen.evaluation.RankBasedMetricResults
Average Precision Score	The area under the precision-recall curve, between [0.0, 1.0]. Higher is better.	sklearn	pykeen.evaluation.SklearnMetricResults
Hits At K	The hits at k for different values of k, i.e. the relative frequency of ranks not larger than k. Higher is better.	rankbased	pykeen.evaluation.RankBasedMetricResults
Mean Rank	The mean over all ranks: mean_i r_i. Lower is better.	rankbased	pykeen.evaluation.RankBasedMetricResults
Mean Reciprocal Rank	The mean over all reciprocal ranks: mean_i (1/r_i). Higher is better.	rankbased	pykeen.evaluation.RankBasedMetricResults
Roc Auc Score	The area under the ROC curve between [0.0, 1.0]. Higher is better.	sklearn	pykeen.evaluation.SklearnMetricResults

Trackers (5)

Name	Reference	Description
csv	pykeen.trackers.CSVResultTracker	Tracking results to a CSV file.
json	pykeen.trackers.JSONResultTracker	Tracking results to a JSON lines file.
mlflow	pykeen.trackers.MLFlowResultTracker	A tracker for MLflow.
neptune	pykeen.trackers.NeptuneResultTracker	A tracker for Neptune.ai.
wandb	pykeen.trackers.WANDBResultTracker	A tracker for Weights and Biases.

Hyper-parameter Optimization

Samplers (3)

Name	Reference	Description
grid	optuna.samplers.GridSampler	Sampler using grid search.
random	optuna.samplers.RandomSampler	Sampler using random sampling.
tpe	optuna.samplers.TPESampler	Sampler using TPE (Tree-structured Parzen Estimator) algorithm.

Any sampler class extending the optuna.samplers.BaseSampler, such as their sampler implementing the CMA-ES algorithm, can also be used.

Experimentation

Reproduction

PyKEEN includes a set of curated experimental settings for reproducing past landmark experiments. They can be accessed and run like:

pykeen experiments reproduce tucker balazevic2019 fb15k

Where the three arguments are the model name, the reference, and the dataset. The output directory can be optionally set with -d.

Ablation

PyKEEN includes the ability to specify ablation studies using the hyper-parameter optimization module. They can be run like:

pykeen experiments ablation ~/path/to/config.json

Large-scale Reproducibility and Benchmarking Study

We used PyKEEN to perform a large-scale reproducibility and benchmarking study which are described in our article:

@article{ali2020benchmarking,
  title={Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework},
  author={Ali, Mehdi and Berrendorf, Max and Hoyt, Charles Tapley and Vermue, Laurent and Galkin, Mikhail and Sharifzadeh, Sahand and Fischer, Asja and Tresp, Volker and Lehmann, Jens},
  journal={arXiv preprint arXiv:2006.13365},
  year={2020}
}

We have made all code, experimental configurations, results, and analyses that lead to our interpretations available at https://github.com/pykeen/benchmarking.

Contributing

Contributions, whether filing an issue, making a pull request, or forking, are appreciated. See CONTRIBUTING.md for more information on getting involved.

Acknowledgements

Supporters

This project has been supported by several organizations (in alphabetical order):

• Bayer
• CoronaWhy
• Enveda Biosciences
• Fraunhofer Institute for Algorithms and Scientific Computing
• Fraunhofer Institute for Intelligent Analysis and Information Systems
• Fraunhofer Center for Machine Learning
• Ludwig-Maximilians-Universität München
• Munich Center for Machine Learning (MCML)
• Siemens
• Smart Data Analytics Research Group (University of Bonn & Fraunhofer IAIS)
• Technical University of Denmark - DTU Compute - Section for Cognitive Systems
• Technical University of Denmark - DTU Compute - Section for Statistics and Data Analysis
• University of Bonn

Logo

The PyKEEN logo was designed by Carina Steinborn.

Citation

If you have found PyKEEN useful in your work, please consider citing our article:

@article{ali2020pykeen,
  title={PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Emebddings},
  author={Ali, Mehdi and Berrendorf, Max and Hoyt, Charles Tapley and Vermue, Laurent and Sharifzadeh, Sahand and Tresp, Volker and Lehmann, Jens},
  journal={arXiv preprint arXiv:2007.14175},
  year={2020}
}