AI RESEARCH
SP-GCRL: Influence Maximization on Incomplete Social Graphs
arXiv CS.AI
•
ArXi:2605.12513v1 Announce Type: cross Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial observability. We first