Home  | Publications | ABH+21

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

MCML Authors

Link to Profile Volker Tresp

Volker Tresp

Prof. Dr.

Principal Investigator

Database Systems, Data Mining and AI

Abstract

Recently, knowledge graph embeddings (KGEs) have received significant attention, and several software libraries have been developed for training and evaluation. While each of them addresses specific needs, we report on a community effort to a re-design and re-implementation of PyKEEN, one of the early KGE libraries. PyKEEN 1.0 enables users to compose knowledge graph embedding models based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. It allows users to measure each component’s influence individually on the model’s performance. Besides, an automatic memory optimization has been realized in order to optimally exploit the provided hardware. Through the integration of Optuna, extensive hyper-parameter optimization (HPO) functionalities are provided.

article

Journal of Machine Learning Research

22.82. Mar. 2021.
Top Journal

Authors

M. Ali • M. Berrendorf • C. T. Hoyt • L. Vermue • S. Sharifzadeh • V. Tresp • J. Lehmann

Links

PDF

Research Area

 A3 | Computational Models

BibTeXKey: ABH+21

Back to Top