Scaling up Dynamic Edge Partition Models via Stochastic Gradient MCMC

arXiv:2403.00044v1 Announce Type: cross
Abstract: The edge partition model (EPM) is a generative model for extracting an overlapping community structure from static graph-structured data. In the EPM, the gamma process (GaP) prior is adopted to infer the appropriate number of latent communities, and each vertex is endowed with a gamma distributed positive memberships vector. Despite having many attractive properties, inference in the EPM is typically performed using Markov chain Monte Carlo (MCMC) methods that prevent it from being applied to …

abstract arxiv communities community cs.ai cs.lg cs.si data dynamic edge gap generative gradient graph mcmc prior process scaling scaling up stochastic structured data the edge type vertex via