GVE-Leiden outperforms original Leiden, igraph Leiden, and NetworKit Leiden in community detection speed and quality.
The author presents GVE-Leiden as an optimized parallel implementation of the Leiden algorithm for community detection on shared memory multicore systems, outperforming other implementations significantly.
GSL-LPA introduces a parallel implementation of LPA to address internally-disconnected communities, outperforming existing methods significantly.
The author explores the integration of vectorial edge covariates in community detection using the VEC-SBM, showing significant improvements in signal-to-noise ratio and clustering accuracy.