PyKEEN Files

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.

Models and Layers

• 🔧✈️ Fix TransH by @mberr in https://github.com/pykeen/pykeen/pull/1057
• ♚♔ Update ConvKB interaction by @mberr in https://github.com/pykeen/pykeen/pull/1065
• 🐸🫖 Fix QuatE by @mberr in https://github.com/pykeen/pykeen/pull/1056
• 🐸🫖 Fix failing QuatE tests by @mberr in https://github.com/pykeen/pykeen/pull/1070
• 🩹💯 Fix typo in OpenEA graph size by @dobraczka in https://github.com/pykeen/pykeen/pull/1073
• 🌑⛱️ Inductive ERModel base class by @mberr in https://github.com/pykeen/pykeen/pull/1106
• 🏋️ 🔧 Kwargs fix for edge weighting in CompGCNLayer by @migalkin in https://github.com/pykeen/pykeen/pull/1138
• ↔️⭐ Merge ComplEx interaction by @mberr in https://github.com/pykeen/pykeen/pull/1103
• ↔️⭐ Merge AutoSF interaction by @mberr in https://github.com/pykeen/pykeen/pull/1112
• 🦷 🔄 Extract inversion utilities by @cthoyt in https://github.com/pykeen/pykeen/pull/1203

NodePiece

• 📿 🧩 Support disconnected nodes in the Relation tokenizer by @migalkin in https://github.com/pykeen/pykeen/pull/1064
• ⚙️🔢 Fix InductiveNodePiece for parametric aggregations by @mberr in https://github.com/pykeen/pykeen/pull/1104

Documentation

• 🖊️📖 Fix typo in tutorial by @mberr in https://github.com/pykeen/pykeen/pull/1067

Performance

• 🍭 🚀 Add optional dep for opt_einsum by @mberr in https://github.com/pykeen/pykeen/pull/1058
• ⚽ 🔧 Properly shuttle tensors to CPU in rank-based evaluator by @Allaway11 in https://github.com/pykeen/pykeen/pull/1076
• 🍭🧑‍🚀 Update remaining einsum usages by @mberr in https://github.com/pykeen/pykeen/pull/1068
• ♻️⚙️ Re-use AMO for predict_triples_df by @mberr in https://github.com/pykeen/pykeen/pull/1089

Pipeline and Prediction

• 🔮☕ Custom Prediction Filtering by @mberr in https://github.com/pykeen/pykeen/pull/1090
• 🪓💻 Split Pipeline Code by @mberr in https://github.com/pykeen/pykeen/pull/1075
• 🔮🤔 Upgrade Prediction Consumers by @mberr in https://github.com/pykeen/pykeen/pull/1078
• 🌀 🏴‍☠️ Clean up inverse triples arguments by @cthoyt in https://github.com/pykeen/pykeen/pull/1092
• 🐛🐔 Fixing bug with index-error for predict.consume_scores by @AImenes in https://github.com/pykeen/pykeen/pull/1157

Representation

• 🔵🟦 Approximate other representation with Low-Rank by @mberr in https://github.com/pykeen/pykeen/pull/1091
• 🗿📖 Update text-based representation tutorial by @mberr in https://github.com/pykeen/pykeen/pull/1147
• 📜🔧 Fix labels not being converted to list by @mberr in https://github.com/pykeen/pykeen/pull/1209
• 🪞🧬 Text representation for biomedical entities via PyOBO by @cthoyt in https://github.com/pykeen/pykeen/pull/1055

Training and Negative Sampling

• ☺️🫖 Relax Slicing Check by @mberr in https://github.com/pykeen/pykeen/pull/1216
• 🪞🚆 Symmetric LCWA by @mberr in https://github.com/pykeen/pykeen/pull/1098
• 🫴🔋 Fix to pass any negative sampler kwargs through if present by @sbonner0 in https://github.com/pykeen/pykeen/pull/1119
• 💾🚆 Fix re-loading training triples by @mberr in https://github.com/pykeen/pykeen/pull/1185

Loss

• Remove unnecessary unsqueezing in MRL by @sbonner0 in https://github.com/pykeen/pykeen/pull/1128
• :book: :hammer_and_wrench: Fix losses docs typos by @nicolafan in https://github.com/pykeen/pykeen/pull/1200

Metrics and Evaluation

• 🔍📈 Fix MacroRankBasedEvaluator share precomputed weights for different triples by @mberr in https://github.com/pykeen/pykeen/pull/1079
• 🧮🪞 Rank-Based Metrics with Confidence Estimates via Bootstrapping by @mberr in https://github.com/pykeen/pykeen/pull/1084
• Incremental ranks by @mberr in https://github.com/pykeen/pykeen/pull/1083
• 😮🪑 Add basic support of OGB's evaluation by @mberr in https://github.com/pykeen/pykeen/pull/1088
• 😮🪑 Add OGB Evaluator by @mberr in https://github.com/pykeen/pykeen/pull/948
• 🌪️➰ Evaluation loop and filter triples by @mberr in https://github.com/pykeen/pykeen/pull/1214
• ⛳💌 Separately Expose Clearing of Intermediate Evaluator Results by @mberr in https://github.com/pykeen/pykeen/pull/1195

Lightning

• ⚡🩹 Fix lightning training without validation by @mberr in https://github.com/pykeen/pykeen/pull/1158
• ⚡🧪 Bring back lightning tests by @mberr in https://github.com/pykeen/pykeen/pull/1191

Misc

• 📌🖼️ Fix plotting utility by @mberr in https://github.com/pykeen/pykeen/pull/1072
• ☁️☀️ Fix word cloud by @mberr in https://github.com/pykeen/pykeen/pull/1081
• ✂️⌨️ Remove unused code by @mberr in https://github.com/pykeen/pykeen/pull/1095
• 💲🐚 Remove $ sign from README shell examples by @mberr in https://github.com/pykeen/pykeen/pull/1101
• 🩹🧑‍🏫 Fix scikit-learn dependency by @dobraczka in https://github.com/pykeen/pykeen/pull/1122
• 👷🚇 Fix CI failure due to new versions by @mberr in https://github.com/pykeen/pykeen/pull/1170
• 🩹🪟 Fix Windows installation instructions by @jamesmyatt in https://github.com/pykeen/pykeen/pull/1164
• 🧹🐻 Cleanup before 1.9 release by @cthoyt in https://github.com/pykeen/pykeen/pull/1204
• 🩹⚙️ Include result_tracker field in dict returned by _get_best_study_config() by @AntonisKl in https://github.com/pykeen/pykeen/pull/1206

New Contributors

• @Allaway11 made their first contribution in https://github.com/pykeen/pykeen/pull/1076
• @jamesmyatt made their first contribution in https://github.com/pykeen/pykeen/pull/1164
• @AImenes made their first contribution in https://github.com/pykeen/pykeen/pull/1157
• @nicolafan made their first contribution in https://github.com/pykeen/pykeen/pull/1200
• @AntonisKl made their first contribution in https://github.com/pykeen/pykeen/pull/1206

Full Changelog: https://github.com/pykeen/pykeen/compare/v1.9.0...v1.10.0