Book
Open access
Aug 2026
Invariant Structure Learning with Pre-trained Language Models for Spatio-temporal Graph
InvSTG-PLM, an invariance-aware spatiotemporal graph learning framework that grounds PLMs in invariant structures, is proposed and a deterministic robustness bound is justified, showing that mean–variance control upper bounds worst-case risk over simulated environments.
Ting Wang, Duo Zhou, Daqian Shi et al.
· Proceedings of the 32nd ACM... · 0 citations