PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings

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.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Link Prediction on WN18 (training time (s) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction WN18 LibKGE (ruffinelli2020you) training time (s) 10 # 2
Link Prediction WN18 OpenKE (han2018openke) training time (s) 11 # 3
Link Prediction WN18 GraphVite (zhu2019graphvite) training time (s) 6 # 1

Methods


No methods listed for this paper. Add relevant methods here