STEC-Net combines GCNs with GRU-updated weights and temporal GRUs plus SOM clustering to discover communities in dynamic networks and reports better purity, NMI, homogeneity and completeness than traditional methods on four network types.
In: Proceedings of the 20th International Conference on Knowledge Discovery and Data Mining, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
STEC-Net: A Spatiotemporal Graph Neural Framework for Community Discovery in Dynamic Social Networks
STEC-Net combines GCNs with GRU-updated weights and temporal GRUs plus SOM clustering to discover communities in dynamic networks and reports better purity, NMI, homogeneity and completeness than traditional methods on four network types.