# Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework

arXiv: https://arxiv.org/abs/2602.04153 · HTML: https://mlsanity.com/paper/2602.04153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 3 of 3)

- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting](https://mlsanity.com/paper/2004.08038/) (2020)
- [Bayesian Machine Learning meets Formal Methods: An application to spatio-temporal data](https://mlsanity.com/paper/2110.01360/) (2021)

## Abstract (arXiv)

Multivariate time series forecasting in graph-structured domains is critical for real-world applications, yet existing spatiotemporal models often suffer from performance degradation under data scarcity and cross-domain shifts. We address these challenges through the lens of structure-aware context selection. We propose TL-GPSTGN, a transfer-oriented spatiotemporal framework that enhances sample efficiency and out-of-distribution generalization by selectively pruning non-optimized graph context. Specifically, our method employs information-theoretic and correlation-based criteria to extract structurally informative subgraphs and features, resulting in a compact, semantically grounded representation. This optimized context is subsequently integrated into a spatiotemporal convolutional architecture to capture complex multivariate dynamics. Evaluations on large-scale traffic benchmarks demonstrate that TL-GPSTGN consistently outperforms baselines in low-data transfer scenarios. Our findings suggest that explicit context pruning serves as a powerful inductive bias for improving the robustness of graph-based forecasting models.