PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings
Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Sahand Sharifzadeh, Volker Tresp, Jens Lehmann
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/pykeen/pykeenOfficialIn paperpytorch★ 1,963
- github.com/SmartDataAnalytics/PyKEENpytorch★ 1,964
Abstract
Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| WN18 | GraphVite (zhu2019graphvite) | training time (s) | 6 | — | Unverified |
| WN18 | LibKGE (ruffinelli2020you) | training time (s) | 10 | — | Unverified |
| WN18 | OpenKE (han2018openke) | training time (s) | 11 | — | Unverified |