SPACED: A Novel Deep Learning Method for Community Detection in Social Networks

Mohammed Tirichine, Nassim Ameur, Younes Boukacem, Hatem Abdelmoumen, Hodhaifa Benouaklil, Samy Ghebache, Boualem Hamroune, Malika Bessedik, Malika Bessedik, Fatima Benbouzid-Si Tayeb, Fatima Benbouzid-Si Tayeb, Riyadh Baghdadi

2024

Abstract

Community detection is a landmark problem in social network analysis. To address this challenge, we propose SPACED: Spaced Positional Autoencoder for Community Embedding Detection, a deep learning-based approach designed to effectively tackle the complexities of community detection in social networks. SPACED generates neighborhood-aware embeddings of network nodes using an autoencoder architecture. These embeddings are then refined through a mixed learning strategy with generated community centers, making them more community-aware. This approach helps unravel network communities through an appropriate clustering strategy. Experimental evaluations across synthetic and real-world networks, as well as comparisons with state-of-the-art methods, demonstrate the high competitiveness and often superiority of SPACED for community detection while maintaining reasonable time complexities.

Paper Citation

in Harvard Style

Tirichine M., Ameur N., Boukacem Y., Abdelmoumen H., Benouaklil H., Ghebache S., Hamroune B., Bessedik M., Benbouzid-Si Tayeb F. and Baghdadi R. (2024). SPACED: A Novel Deep Learning Method for Community Detection in Social Networks. In Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-718-4, SciTePress, pages 141-152. DOI: 10.5220/0013070100003825

in Bibtex Style

@conference{webist24,
author={Mohammed Tirichine and Nassim Ameur and Younes Boukacem and Hatem Abdelmoumen and Hodhaifa Benouaklil and Samy Ghebache and Boualem Hamroune and Malika Bessedik and Fatima Benbouzid-Si Tayeb and Riyadh Baghdadi},
title={SPACED: A Novel Deep Learning Method for Community Detection in Social Networks},
booktitle={Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2024},
pages={141-152},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013070100003825},
isbn={978-989-758-718-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - SPACED: A Novel Deep Learning Method for Community Detection in Social Networks
SN - 978-989-758-718-4
AU - Tirichine M.
AU - Ameur N.
AU - Boukacem Y.
AU - Abdelmoumen H.
AU - Benouaklil H.
AU - Ghebache S.
AU - Hamroune B.
AU - Bessedik M.
AU - Benbouzid-Si Tayeb F.
AU - Baghdadi R.
PY - 2024
SP - 141
EP - 152
DO - 10.5220/0013070100003825
PB - SciTePress