TY - GEN
T1 - SPACED
T2 - 20th International Conference on Web Information Systems and Technologies, WEBIST 2024
AU - Tirichine, Mohammed
AU - Ameur, Nassim
AU - Boukacem, Younes
AU - Abdelmoumen, Hatem M.
AU - Benouaklil, Hodhaifa
AU - Ghebache, Samy
AU - Hamroune, Boualem
AU - Bessedik, Malika
AU - Tayeb, Fatima Benbouzid Si
AU - Baghdadi, Riyadh
N1 - Publisher Copyright:
Copyright © 2024 by SCITEPRESS.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Community Detection
KW - Community Embedding
KW - Deep Learning
KW - Node Embedding
KW - Social Network
UR - http://www.scopus.com/inward/record.url?scp=85217158496&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85217158496&partnerID=8YFLogxK
U2 - 10.5220/0013070100003825
DO - 10.5220/0013070100003825
M3 - Conference contribution
AN - SCOPUS:85217158496
T3 - International Conference on Web Information Systems and Technologies, WEBIST - Proceedings
SP - 141
EP - 152
BT - Proceedings of the 20th International Conference on Web Information Systems and Technologies, WEBIST 2024
A2 - Penalvo, Francisco Garcia
A2 - Aberer, Karl
A2 - Marchiori, Massimo
PB - Science and Technology Publications, Lda
Y2 - 17 November 2024 through 19 November 2024
ER -