EvalNE
Library for evaluation of graph representation learning methods.
Description:
EvalNE is an open-source Python library designed for assessing and comparing the performance of Network Embedding (NE) methods on Link Prediction (LP), Sign prediction (SP), Network Reconstruction (NR) and Node Classification (NC) tasks. The library intends to simplify these complex and time-consuming evaluation processes by providing automation and abstraction of tasks such as hyper-parameter tuning and model validation, node and edge sampling, node-pair embedding computation, results reporting and data visualization.
The library can be used both as a command line tool and an API. In its current version, EvalNE can evaluate unweighted directed and undirected simple networks.
The library is maintained by Alexandru Mara. The full documentation of EvalNE is hosted by Read the Docs and can be found here.
More Information:
Originates from the AI-Driven Data Science research challenge (FAIR 2019–2023).
Responsible Research Leads: Tijl De Bie, Jefrey Lijffijt
Authors: Alexandru Mara, Jefrey Lijffijt, Tijl De Bie
Programming Language: Python
Categories: Networks and graphs
Publications:
A. Mara, J. Lijffijt, T. De Bie, "EvalNE: A Framework for Evaluating Network Embeddings on Link Prediction", rarXiv:1901.09691v1 [cs.SI] , 2019