We have recently released EvalNE, an open-source Python library designed for assessing and comparing the performance of Network Embedding (NE) methods on Link Prediction (LP) tasks. The library intends to simplify the complex and time-consuming process of evaluating NE methods and to partially address the reproducibility crisis in this subfield of Machine Learning.
The code is available on GitHub: https://github.com/Dru-Mara/EvalNE
The documentation is hosted by Read the Docs: https://evalne.readthedocs.io/en/latest/index.html#
Authors: Alexandru Mara, Jefrey Lijffijt and Tijl De Bie.