AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging

TL;DR

AnchorGK is a novel graph learning framework that improves inductive spatio-temporal kriging by using anchor-based stratification to handle sparse sensor data and heterogeneous features, leading to superior performance.

Contribution

It introduces an anchor-based stratification method and a dual-view graph learning layer to better model correlations and utilize features in spatio-temporal kriging.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively handles feature incompleteness and data sparsity

Provides a systematic approach for inductive spatio-temporal inference

Abstract

Spatio-temporal kriging is a fundamental problem in sensor networks, driven by the sparsity of deployed sensors and the resulting missing observations. Although recent approaches model spatial and temporal correlations, they often under-exploit two practical characteristics of real deployments: the sparse spatial distribution of locations and the heterogeneous availability of auxiliary features across locations. To address these challenges, we propose AnchorGK, an Anchor-based Incremental and Stratified Graph Learning framework for inductive spatio-temporal kriging. AnchorGK introduces anchor locations to stratify the data in a principled manner. Anchors are constructed according to feature availability, and strata are then formed around these anchors. This stratification serves two complementary roles. First, it explicitly represents and continuously updates correlations between unobserved regions and surrounding observed locations within a graph learning framework. Second, it enables the systematic use of all available features across strata via an incremental representation mechanism, mitigating feature incompleteness without discarding informative signals. Building on the stratified structure, we design a dual-view graph learning layer that jointly aggregates feature-relevant and location-relevant information, learning stratum-specific representations that support accurate inference under inductive settings. Extensive experiments on multiple benchmark datasets demonstrate that AnchorGK consistently outperforms state-of-the-art baselines for spatio-temporal kriging.