RaDE: A Rank-based Graph Embedding Approach

Filipe Alves de Fernando, Daniel Carlos Guimarães Pedronette, Gustavo José de Sousa, Lucas Pascotti Valem, Ivan Rizzo Guilherme

2020

Abstract

Due to possibility of capturing complex relationships existing between nodes, many application benefit of being modeled with graphs. However, performance issues can be observed on large scale networks, making it computationally unfeasible to process information in various scenarios. Graph Embedding methods are usually used for finding low-dimensional vector representations for graphs, preserving its original properties such as topological characteristics, affinity and shared neighborhood between nodes. In this way, retrieval and machine learning techniques can be exploited to execute tasks such as classification, clustering, and link prediction. In this work, we propose RaDE (Rank Diffusion Embedding), an efficient and effective approach that considers rank-based graphs for learning a low-dimensional vector. The proposed approach was evaluated on 7 network datasets such as a social, co-reference, textual and image networks, with different properties. Vector representations generated with RaDE achieved effective results in visualization and retrieval tasks when compared to vector representations generated by other recent related methods.

Paper Citation

in Harvard Style

Alves de Fernando F., Pedronette D., José de Sousa G., Valem L. and Guilherme I. (2020). RaDE: A Rank-based Graph Embedding Approach. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 142-152. DOI: 10.5220/0008985901420152

in Bibtex Style

@conference{visapp20,
author={Filipe Alves de Fernando and Daniel Carlos Guimarães Pedronette and Gustavo José de Sousa and Lucas Pascotti Valem and Ivan Rizzo Guilherme},
title={RaDE: A Rank-based Graph Embedding Approach},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={142-152},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008985901420152},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - RaDE: A Rank-based Graph Embedding Approach
SN - 978-989-758-402-2
AU - Alves de Fernando F.
AU - Pedronette D.
AU - José de Sousa G.
AU - Valem L.
AU - Guilherme I.
PY - 2020
SP - 142
EP - 152
DO - 10.5220/0008985901420152
PB - SciTePress