๐ค A Python library for learning and evaluating knowledge graph embeddings
MIT License
Bot releases are hidden (Show)
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.10.1...v1.10.2
Published by cthoyt over 1 year ago
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.10.0...v1.10.1
Published by cthoyt over 1 year ago
The PyKEEN 1.10 release contains a huge variety of bug fixes, performance improvements, and new features. A few highlights include symmetric sLCWA training loop, evaluation with OGB, biomedical entity representation modules, low-rank representation approximation, and many improvements to the prediction pipeline.
CompGCNLayer
by @migalkin in https://github.com/pykeen/pykeen/pull/1138
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.9.0...v1.10.0
Published by cthoyt about 2 years ago
The theme of this release of PyKEEN is centered on new and exciting representations to bring more kinds of data (text, image, scalar data) into training in an elegant way. Several of these contribute to new functionality for NodePiece.
MetisAnchorTokenizer
by @migalkin in https://github.com/pykeen/pykeen/pull/1026
_safe_evaluate()
by @migalkin in https://github.com/pykeen/pykeen/pull/1041
torch_ppr
by @mberr in https://github.com/pykeen/pykeen/pull/995
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.8.2...v1.9.0
Published by cthoyt over 2 years ago
nan
strings by @SenJia in https://github.com/pykeen/pykeen/pull/883
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.8.1...v1.8.2
Published by cthoyt over 2 years ago
PyKEEN 1.8.1 contains a few critical bug fixes along with some other cool updates.
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.8.0...v1.8.1
Published by cthoyt over 2 years ago
Among a ton of updates since the beginning of the year, PyKEEN v1.8.0 has three major themes:
mode
parameter by @cthoyt in https://github.com/pykeen/pykeen/pull/769
slice_size
by @cthoyt in https://github.com/pykeen/pykeen/pull/729
setup.py
and Makefile
for building the docs by @cthoyt in https://github.com/pykeen/pykeen/pull/761
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.7.0...v1.8.0
ERModel
's __init__
by @mberr in https://github.com/pykeen/pykeen/pull/717
predict_*
methods when using inverse relations by @mberr in https://github.com/pykeen/pykeen/pull/699
predict_*
methods by @mberr in https://github.com/pykeen/pykeen/pull/658
evaluate()
for easier relation filtering by @mberr in https://github.com/pykeen/pykeen/pull/391
rexmex
by @cthoyt in https://github.com/pykeen/pykeen/pull/668
np.loadtxt
to pandas.read_csv
by @mberr in https://github.com/pykeen/pykeen/pull/695
torch.finfo
to determine suitable epsilon values by @mberr in https://github.com/pykeen/pykeen/pull/626
torch.isin
instead of own implementation by @mberr in https://github.com/pykeen/pykeen/pull/635
torch.inference_mode
instead of torch.no_grad
by @sbonner0 in https://github.com/pykeen/pykeen/pull/604
loss_kwargs
by @mali-git in https://github.com/pykeen/pykeen/pull/656
hpo_pipeline
by @mberr in https://github.com/pykeen/pykeen/pull/724
This release is only compatible with PyTorch 1.9+. Because of some changes,
it's now pretty non-trivial to support both, so moving forwards PyKEEN will
continue to support the latest version of PyTorch and try its best to keep
backwards compatibility.
If you're interested in any of these, please get in touch with us regarding an upcoming publication.
pipeline()
using an Interaction module rather than a Model (https://github.com/pykeen/pykeen/pull/326, https://github.com/pykeen/pykeen/pull/330).class_resolver
package (https://github.com/pykeen/pykeen/pull/321, https://github.com/pykeen/pykeen/pull/327)docdata
package is now used to parse structured information out of the model and dataset documentation in order to make a more informative README with links to citations (https://github.com/pykeen/pykeen/pull/303).We skipped version 1.2.0 because we made an accidental release before this version was ready. We're only human, and are looking into improving our release workflow to live in CI/CD so something like this doesn't happen again. However, as an end user, this won't have an effect on you.
pykeen version
command for more easily reporting your environment in issues (https://github.com/pykeen/pykeen/issues/251)p
value for the L_p norm in TransE.__init__()
function of each KGEM class and can be configured. A future update will enable HPO on these as well (https://github.com/pykeen/pykeen/issues/282).This release contains a few big refactors. Most won't affect end-users, but if you're writing your own PyKEEN models, these are important. Many of them are motivated to make it possible to introduce a new interface that makes it much easier for researchers (who shouldn't have to understand the inner workings of PyKEEN) to make new models.
torch.device
when instantiated.pykeen.nn.Embedding
class has been improved in several ways:
doctests
(https://github.com/pykeen/pykeen/issues/291)We've made some improvements to the pykeen.triples.TriplesFactory
to facilitate loading even larger datasets (https://github.com/pykeen/pykeen/issues/216). However, this required an interface change. This will affect any code that loads custom triples. If you're loading triples from a path, you should now use:
path = ...
# Old (doesn't work anymore)
tf = TriplesFactory(path=path)
# New
tf = TriplesFactory.from_path(path)
While refactoring the base model class, we excised the prediction functionality to a new module pykeen.models.predict
(docs: https://pykeen.readthedocs.io/en/latest/reference/predict.html#functions). We also renamed some of the prediction functions inside the base model to make them more consistent, but we now recommend you use the functions from pykeen.models.predict
instead.
Model.predict_heads()
-> Model.get_head_prediction_df()
Model.predict_relations()
-> Model.get_head_prediction_df()
Model.predict_tails()
-> Model.get_head_prediction_df()
Model.score_all_triples()
-> Model.get_all_prediction_df()
This is the last release before the PyKEEN 1.0 release, be prepared for major changes.
Note! If you've come this far looking for old releases of PyKEEN, we were unfortunately not able to retain them when we moved the code to this new organization. Please see PyPI for a more complete release history (https://pypi.org/project/pykeen/#history) or the Zenodo record associated with SmartDataAnalytics/PyKEEN