Addressing Spatial Indistinguishability in Spatiotemporal Prediction via Optimal Transport-Guided Masking

2026-09-28

AI Summary

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.

Abstract

Spatiotemporal prediction aims to learn discriminative representations from correlated temporal signals over spatial structures for accurate future inference. A central challenge is \emph{spatial indistinguishability}: different nodes may share similar historical patterns yet evolve toward divergent futures, severely degrading forecasting performance in real-world sensor networks. Existing embedding-based and graph neural network (GNN)-based approaches can partially detect such ambiguous nodes but rely on historical similarity, struggling to capture \emph{future behavioral divergence}. We propose \textbf{STOT} (\textbf{S}patio\textbf{T}emporal \textbf{O}ptimal \textbf{T}ransport), a self-supervised framework that resolves spatiotemporal ambiguity via structured masking guided by optimal transport. Our key idea treats indistinguishability as a \emph{disambiguation} problem: future states are inferred by exploiting concurrent spatial correlations and their time-varying similarity. We design a similarity-aware metric for dynamic inter-node relationships and an optimal transport-based masking strategy to emphasize ambiguous positions during pre-training. A batch consistency constraint preserves semantic coherence, while a random-walk masking mechanism promotes structured context exploration. Experiments on six real-world datasets show that STOT performs competitively with state-of-the-art baselines on the evaluated benchmarks and improved interpretability through transport-plan visualizations.

Problem

• Spatiotemporal Prediction
• Spatial Indistinguishability
• Future Behavioral Divergence
• Sensor Networks

Innovation

• Spatiotemporal Prediction
• Optimal Transport
• Self-supervised Learning
• Masking Strategy
• Spatial Indistinguishability