EvalNE : a framework for evaluating network embeddings on link prediction

In this paper, we present EvalNE, a Python toolbox for evaluating network embedding methods on link prediction tasks. Link prediction is one of the most popular choices for evaluating the quality of network embeddings. However, the complexity of this task requires a carefully designed evaluation pipeline to provide consistent, reproducible and comparable results. EvalNE simplifies this process by providing automation and abstraction of tasks such as hyper-parameter tuning and model validation, edge sampling and negative edge sampling, computation of edge embeddings from node embeddings, and evaluation metrics. The toolbox allows for the evaluation of any off-the-shelf embedding method without the need to write extra code. Moreover, it can also be used for evaluating link prediction methods and integrates several link prediction heuristics as baselines. Finally, demonstrating the usefulness of EvalNE in practice, we conduct an extensive analysis where we replicate the experimental sections of several influential papers in the community