๐ค A Python library for learning and evaluating knowledge graph embeddings
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.10.1...v1.10.2
Full Changelog: https://github.com/pykeen/pykeen/compare/v1.10.0...v1.10.1
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
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
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
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
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.