Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging

arXiv:2509.23631v2 Announce Type: replace Abstract: Inductive kriging estimates values at unobserved locations from sparse sensor data, enabling continuous field reconstruction when dense deployment is impractical. However, common 2 x 2 and 2 x 3 evaluation protocols can leak spatial information through model selection and obscure true out-of-distribution (OOD) behavior. We propose a leakage-free 3 x 3 partition that separates training, validation, and testing in both space and time, so that model fitting, checkpoint selection, and final reporting are performed on distinct spatio-temporal domains. Under this stricter setting, we introduce DRIK (Distribution-Robust Inductive Kriging), a framework with three task-specific mechanisms: Spatial Continuity Regularization (SCR) perturbs coordinates to reduce dependence on one discretized graph; Masked Flow Disambiguation (MFD) prunes ambiguous propagation from zero-padded masked nodes; and Structural Domain Expansion (SDE) uses validation-node topology without labels to reduce train-inference structural mismatch. Experiments on six spatio-temporal datasets show that DRIK consistently outperforms state-of-the-art baselines, reducing MAE by up to 12.48% and achieving lower test-to-validation MAE ratios under leakage-free evaluation. These results indicate that robust inductive kriging requires both leakage-free evaluation and mechanisms that explicitly address the structural shifts introduced by unseen nodes.

Abstract:Inductive kriging estimates values at unobserved locations from sparse sensor data, enabling continuous field reconstruction when dense deployment is impractical. However, common 2 x 2 and 2 x 3 evaluation protocols can leak spatial information through model selection and obscure true out-of-distribution (OOD) behavior. We propose a leakage-free 3 x 3 partition that separates training, validation, and testing in both space and time, so that model fitting, checkpoint selection, and final reporting are performed on distinct spatio-temporal domains. Under this stricter setting, we introduce DRIK (Distribution-Robust Inductive Kriging), a framework with three task-specific mechanisms: Spatial Continuity Regularization (SCR) perturbs coordinates to reduce dependence on one discretized graph; Masked Flow Disambiguation (MFD) prunes ambiguous propagation from zero-padded masked nodes; and Structural Domain Expansion (SDE) uses validation-node topology without labels to reduce train-inference structural mismatch. Experiments on six spatio-temporal datasets show that DRIK consistently outperforms state-of-the-art baselines, reducing MAE by up to 12.48% and achieving lower test-to-validation MAE ratios under leakage-free evaluation. These results indicate that robust inductive kriging requires both leakage-free evaluation and mechanisms that explicitly address the structural shifts introduced by unseen nodes.

31 pages, 10 figures. Accepted for publication in Pattern Recognition

Machine Learning (cs.LG)

arXiv:2509.23631 [cs.LG]

(or arXiv:2509.23631v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2509.23631 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1016/j.patcog.2026.114638 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging

Related coverage