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

arXiv: https://arxiv.org/abs/2509.23631 · HTML: https://mlsanity.com/paper/2509.23631/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Graph Random Neural Network for Semi-Supervised Learning on Graphs](https://mlsanity.com/paper/2005.11079/) (2020)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [GOOD: A Graph Out-of-Distribution Benchmark](https://mlsanity.com/paper/2206.08452/) (2022)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [Inductive Graph Neural Networks for Spatiotemporal Kriging](https://mlsanity.com/paper/2006.07527/) (2020)
- [Factorizable Graph Convolutional Networks](https://mlsanity.com/paper/2010.05421/) (2020)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [Graph Rationalization with Environment-based Augmentations](https://mlsanity.com/paper/2206.02886/) (2022)
- [PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation](https://mlsanity.com/paper/2302.09746/) (2023)
- [UrbanFM: Inferring Fine-Grained Urban Flows](https://mlsanity.com/paper/1902.05377/) (2019)
- [Kriging Convolutional Networks](https://mlsanity.com/paper/2306.09463/) (2023)
- [Metropolis-Hastings Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2203.14082/) (2022)
- [Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging](https://mlsanity.com/paper/2109.12144/) (2021)
- [INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging](https://mlsanity.com/paper/2302.02738/) (2023)
- [Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks](https://mlsanity.com/paper/2212.04983/) (2022)
- [KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy](https://mlsanity.com/paper/2311.02565/) (2023)
- [Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference](https://mlsanity.com/paper/2109.09506/) (2021)

## Abstract (arXiv)

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.