DRIK: Distribution-Robust Inductive Kriging without Information Leakage
This addresses a specific issue in spatio-temporal modeling for sensor networks, offering incremental improvements in robustness and generalization.
The paper tackles the problem of information leakage and poor out-of-distribution generalization in inductive kriging for spatio-temporal estimation by proposing a 3x3 partition to eliminate leakage and introducing DRIK, a distribution-robust approach that achieves up to 12.48% lower MAE on six datasets.
Inductive kriging supports high-resolution spatio-temporal estimation with sparse sensor networks, but conventional training-evaluation setups often suffer from information leakage and poor out-of-distribution (OOD) generalization. We find that the common 2x2 spatio-temporal split allows test data to influence model selection through early stopping, obscuring the true OOD characteristics of inductive kriging. To address this issue, we propose a 3x3 partition that cleanly separates training, validation, and test sets, eliminating leakage and better reflecting real-world applications. Building on this redefined setting, we introduce DRIK, a Distribution-Robust Inductive Kriging approach designed with the intrinsic properties of inductive kriging in mind to explicitly enhance OOD generalization, employing a three-tier strategy at the node, edge, and subgraph levels. DRIK perturbs node coordinates to capture continuous spatial relationships, drops edges to reduce ambiguity in information flow and increase topological diversity, and adds pseudo-labeled subgraphs to strengthen domain generalization. Experiments on six diverse spatio-temporal datasets show that DRIK consistently outperforms existing methods, achieving up to 12.48% lower MAE while maintaining strong scalability.