Learning from Highly Sparse Spatio-temporal Data

Incomplete spatio-temporal data in the real world has spawned much research. However, existing methods often utilize iterative message-passing across temporal and spatial dimensions, resulting in substantial information loss and high computational cost. We provide a theoretical analysis revealing that such iterative models are susceptible to data and graph sparsity, causing unstable performances on different datasets. To overcome these limitations, we introduce a novel method named One-step Propagation and Confidence-based Refinement (OPCR). In the first stage, OPCR leverages inherent spatial and temporal relationships by employing a sparse attention mechanism. These modules propagate limited observations directly to the global context through one-step imputation, which is theoretically affected only by data sparsity. Following this, we assign confidence levels to the initial imputations by correlating missing data with valid data. This confidence-based propagation refines the separate spatial and temporal imputation results through spatio-temporal dependencies. We evaluate the proposed model across various downstream tasks involving highly sparse spatio-temporal data. Empirical results indicate that our model outperforms state-of-the-art imputation methods, demonstrating its effectiveness and robustness.