A Machine Learning Framework for Constructing Heterogeneous Contact Networks: Implications for Epidemic Modelling

Collection of recent arXiv submissions (computer science — social/information networks) covering methods and tools for modeling, simulation, privacy, and data generation on networks. Highlights include: a machine-learning framework to generate population-scale heterogeneous contact networks that preserve age-structured mixing for epidemic modeling; FS_GPlib, a dual-acceleration library for web-scale propagation simulations (claims up to 35k× speedups and billion-edge Monte Carlo runs in seconds); an agentic workflow to generate and iteratively refine synthetic crisis-related tweets for dataset