A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks

Kostas Loumponias, Andreas Kosmatopoulos, Theodora Tsikrika, Stefanos Vrochidis, Ioannis Kompatsiaris

2022

Abstract

The graph embedding process aims to transform nodes and edges into a low dimensional vector space, while preserving the graph structure and topological properties. Random walk based methods are used to capture structural relationships between nodes, by performing truncated random walks. Afterwards, the SkipGram model with the negative sampling approach, is used to calculate the embedded nodes. In this paper, the proposed SkipGram model converges in fewer iterations than the standard one. Furthermore, the community detection and link prediction task is enhanced by the proposed method.

Paper Citation

in Harvard Style

Loumponias K., Kosmatopoulos A., Tsikrika T., Vrochidis S. and Kompatsiaris I. (2022). A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks. In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-584-5, pages 86-93. DOI: 10.5220/0011142000003277

in Bibtex Style

@conference{delta22,
author={Kostas Loumponias and Andreas Kosmatopoulos and Theodora Tsikrika and Stefanos Vrochidis and Ioannis Kompatsiaris},
title={A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks},
booktitle={Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2022},
pages={86-93},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011142000003277},
isbn={978-989-758-584-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks
SN - 978-989-758-584-5
AU - Loumponias K.
AU - Kosmatopoulos A.
AU - Tsikrika T.
AU - Vrochidis S.
AU - Kompatsiaris I.
PY - 2022
SP - 86
EP - 93
DO - 10.5220/0011142000003277