🤖 A Python library for learning and evaluating knowledge graph embeddings

🏅 KG Inductive Link Prediction Challenge (ILPC) 2022

📐 Results for the Ranking Metrics submission @ GLB 2022

A knowledge graph containing 5 million research papers. Uses: compute Erdős numbers, rank influence of cities on research areas, detect whether researchers with the same name are the same person.

A comparison of Knowledge Graph Embedding methods.

A project to predict new repurposed drugs for dengue using a biomedical knowledge graph and graph neural networks.

A place for one-off experiments with PyKEEN that can be re-run anytime

Keywords: PyKEEN / Inductive Reasoning / Deductive Reasoning

PyKEEN benchmarks with airspeed velocity served at https://pykeen.github.io/asv-benchmark/

Combining Query Rewriting (PerfectRef) and Knowledge Graph Embeddings with Complex Query Answering

🪑 Benchmark negative samplers' false negative rate

🌐 The website for PyKEEN and the KEEN universe at https://pykeen.github.io

🪑 Benchmark the bloom filterer at https://pykeen.github.io/bloom-filterer-benchmark/

🪑 Benchmark non-parametric KGE models

🪑 Benchmark collation of negative samples inside the DataLoader