Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Graph Data Augmentation via Contrastive Generator Inversion ()
Mateusz Stolarski, Michał Czuba, Łukasz Kraiński +4
Graphs provide a natural representation of many complex systems, ranging from social platforms to ecosystems. However, the development of graph-based machine learning methods is of…
cs.LG2026
Towards Graph Foundation Models for Dynamics in Complex Networked Systems: Lessons from Super-Spreader Identification in Multilayer Networks
Michał Czuba, Mateusz Stolarski, Adam Piróg +2
Network dynamics - including spreading, influence maximisation, and epidemic modelling - remain largely confined to the transductive paradigm, where models are trained on a single…