Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models

ArXi:2606.04672v1 Announce Type: cross Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal horizons. Existing approaches restrict models to capture one-hop or local temporal neighborhoods and fail to capture multi-hop or global structural patterns.