Addressing Spatial Indistinguishability in Spatiotemporal Prediction via Optimal Transport-Guided Masking
This study addresses the problem of "spatial indistinguishability" in spatiotemporal prediction, where historically similar nodes exhibit divergent future evolutions. To tackle this challenge, we propose STOT, a self-supervised framework that introduces a novel optimal transport-based masking mechanism to transform predictive ambiguity into an active disambiguation task. By integrating batch consistency constraints with random walk strategies, the framework dynamically captures structured node relationships and future behavioral divergence. Extensive experiments demonstrate that STOT achieves state-of-the-art performance across six real-world datasets. Furthermore, visualizing the learned transport plans significantly enhances model interpretability.