Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework
This addresses the problem of robust forecasting in graph-structured domains for applications like traffic management, though it appears incremental as it builds on existing spatiotemporal models with a pruning-based enhancement.
The paper tackles performance degradation in multivariate time series forecasting on graphs under data scarcity and cross-domain shifts by proposing TL-GPSTGN, a transfer-oriented framework that uses structure-aware pruning to enhance sample efficiency and out-of-distribution generalization, resulting in consistent outperformance of baselines on large-scale traffic benchmarks.
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.