AI RESEARCH
Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models
arXiv CS.AI
•
ArXi:2605.13540v1 Announce Type: cross Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs from different domains pose fundamental challenges to unified modeling, as their semantic and temporal patterns are inherently inconsistent, making the multi-domain pre-