How Much Graph Is Too Much? Graph Construction and Exposure in Spatio-Temporal Forecasting
Abstract
Spatio-temporal graph neural networks combine a node's history with information from graph neighbors. The central question is whether graph neighbors provide predictive information beyond each node's own history. Forecast accuracy depends on both the choice of neighbors and the way graph messages enter the temporal model. We study these choices as graph construction and graph exposure on U.S. state unemployment, traffic speed, and electricity demand. Our diagnostic design uses two comparisons: varying exposure while holding the domain graph fixed, and varying construction while holding late gated integration fixed. A GRU using only each node's own history and randomized graph controls help assess what the graph contributes. Under a common change forecasting protocol, the same domain graph can improve or worsen error relative to the GRU across integration designs. Late integration alone is insufficient, while adding a fusion gate yields lower mean error in all three tasks. With late gated integration fixed, a graph based on residual correlations has the lowest mean error among the tested graphs, although randomized graphs perform similarly on unemployment. The findings support evaluating graph construction and integration together, with conclusions tied to the comparisons actually performed.
Related
- Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
- Short-term metro passenger flow forecasting via decoupled spatio-temporal modeling with a diffusion-convergence graph and Swin-Enhanced LSTM
- STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting
- Automated Detection of Match Phases in Football from Spatio-Temporal Tracking Data Using Graph Neural Networks
- ST-GFM: Spectral-Temporal Graph Forecasting with Measured Perturbation Bounds and Masked Spectral Reconstruction
BibTeX
@misc{maru2026much,
title = {{How Much Graph Is Too Much? Graph Construction and Exposure in Spatio-Temporal Forecasting}},
author = {Saj Maru and Qiyu Han and Krishna Mamidala},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.34611},
eprint = {2610.34611},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.34611},
}
RIS
TY - UNPB
TI - How Much Graph Is Too Much? Graph Construction and Exposure in Spatio-Temporal Forecasting
AU - Saj Maru
AU - Qiyu Han
AU - Krishna Mamidala
PY - 2026
DA - 2026/10/25
PB - arXiv
DO - 10.48550/arxiv.2610.34611
UR - https://arxiv.org/abs/2610.34611
AB - Spatio-temporal graph neural networks combine a node's history with information from graph neighbors. The central question is whether graph neighbors provide predictive information beyond each node's own history. Forecast accuracy depends on both the choice of neighbors and the way graph messages enter the temporal model. We study these choices as graph construction and graph exposure on U.S. state unemployment, traffic speed, and electricity demand. Our diagnostic design uses two comparisons: varying exposure while holding the domain graph fixed, and varying construction while holding late gated integration fixed. A GRU using only each node's own history and randomized graph controls help assess what the graph contributes. Under a common change forecasting protocol, the same domain graph can improve or worsen error relative to the GRU across integration designs. Late integration alone is insufficient, while adding a fusion gate yields lower mean error in all three tasks. With late gated integration fixed, a graph based on residual correlations has the lowest mean error among the tested graphs, although randomized graphs perform similarly on unemployment. The findings support evaluating graph construction and integration together, with conclusions tied to the comparisons actually performed.
ER -