Download Latest Version v1.11.1 source code.tar.gz (8.6 MB)
Email in envelope

Get an email when there's a new version of PyKEEN

Home / v1.11.1
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2025-04-24 5.5 kB
v1.11.1 source code.tar.gz 2025-04-24 8.6 MB
v1.11.1 source code.zip 2025-04-24 8.9 MB
Totals: 3 Items   17.5 MB 2

Enhancements

Inductive Models and Datasets

Representations

PyKEEN v1.11.1 introduces several new representations to support scenarios when you can bring your own featurization (such as chemical fingerprints in the cheminformatics domain)

Loss Weights

PyKEEN v1.11.1 introduces loss weights, which influence how much a given triple is weighted in the loss function. They are primarily a tool to shape your optimization criterion, i.e., what you optimize your embedding models on. For example, you may want to focus more or less on certain types of triples because they are more or less important for your application. You can also use loss weights to counteract imbalances in relation frequencies, i.e., to down-weight frequent relation types.

More information at: https://pykeen.readthedocs.io/en/latest/reference/loss_weighting.html

Misc

Removals

Fixes

Documentation

Meta

Testing

Typing and Code Style

New Contributors

Full Changelog: https://github.com/pykeen/pykeen/compare/v1.11.0...v1.11.1

Source: README.md, updated 2025-04-24