Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework

TL;DR

This paper introduces TL-GPSTGN, a transfer-oriented spatiotemporal graph framework that improves multivariate time series forecasting by pruning non-essential graph contexts, enhancing transferability and robustness in data-scarce and cross-domain scenarios.

Contribution

It presents a novel context pruning method using information-theoretic and correlation criteria to improve graph-based forecasting models' transferability and generalization.

Findings

Outperforms baselines in low-data transfer scenarios

Enhances sample efficiency and out-of-distribution generalization

Provides a compact, semantically meaningful graph representation

Abstract

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.