STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach
By: Yujie Li , Zezhi Shao , Chengqing Yu and more
Potential Business Impact:
Fixes missing data for better predictions.
Spatio-temporal tasks often encounter incomplete data arising from missing or inaccessible sensors, making spatio-temporal kriging crucial for inferring the completely missing temporal information. However, current models struggle with ensuring the validity and generalizability of inferred spatio-temporal patterns, especially in capturing dynamic spatial dependencies and temporal shifts, and optimizing the generalizability of unknown sensors. To overcome these limitations, we propose Spatio-Temporal Aware Graph Adversarial Neural Network (STA-GANN), a novel GNN-based kriging framework that improves spatio-temporal pattern validity and generalization. STA-GANN integrates (i) Decoupled Phase Module that senses and adjusts for timestamp shifts. (ii) Dynamic Data-Driven Metadata Graph Modeling to update spatial relationships using temporal data and metadata; (iii) An adversarial transfer learning strategy to ensure generalizability. Extensive validation across nine datasets from four fields and theoretical evidence both demonstrate the superior performance of STA-GANN.
Similar Papers
A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction
Machine Learning (CS)
Predicts traffic jams better by remembering past patterns.
Leveraging Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting
Machine Learning (CS)
Predicts store sales better by seeing how stores affect each other.
SpikeSTAG: Spatial-Temporal Forecasting via GNN-SNN Collaboration
Machine Learning (CS)
Predicts long-term data patterns more accurately