Advanced search
1 file | 177.64 KB Add to list

EvalNE : a framework for evaluating network embeddings on link prediction

(2019)
Author
Organization
Abstract
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 in order 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 any other link prediction method, and integrates several link prediction heuristics as baselines.
Keywords
Network Embedding, Link Prediction, Evaluation, Edge Sampling, Graphs

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 177.64 KB

Citation

Please use this url to cite or link to this publication:

MLA
Mara, Alexandru Cristian. “EvalNE : a Framework for Evaluating Network Embeddings on Link Prediction.” 2019 : n. pag. Print.
APA
Mara, A. C. (2019). EvalNE : a framework for evaluating network embeddings on link prediction.
Chicago author-date
Mara, Alexandru Cristian. 2019. “EvalNE : a Framework for Evaluating Network Embeddings on Link Prediction.”
Chicago author-date (all authors)
Mara, Alexandru Cristian. 2019. “EvalNE : a Framework for Evaluating Network Embeddings on Link Prediction.”
Vancouver
1.
Mara AC. EvalNE : a framework for evaluating network embeddings on link prediction. 2019.
IEEE
[1]
A. C. Mara, “EvalNE : a framework for evaluating network embeddings on link prediction.” 2019.
@misc{8592096,
  abstract     = {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 in order 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 any other link prediction method, and integrates several link prediction heuristics as baselines.},
  author       = {Mara, Alexandru Cristian},
  keywords     = {Network Embedding,Link Prediction,Evaluation,Edge Sampling,Graphs},
  title        = {EvalNE : a framework for evaluating network embeddings on link prediction},
  url          = {https://arxiv.org/abs/1901.09691},
  year         = {2019},
}