arXiv Statistics ML
How Much Graph Is Too Much? Graph Construction and Exposure in Spatio-Temporal Forecasting
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Sep 22
GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting
arXiv:2609.24609v1 Announce Type: new Abstract: Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) prov...
arXiv Machine Learning
Oct 7
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Models
arXiv:2608.20980v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are routinely employed for spatiotemporal forecasting, yet their performance across widely used benchmark datasets is...
arXiv Machine Learning
Jul 17
What Do Temporal Graph Learning Models Learn?
arXiv:2510. 09416v4 Announce Type: replace Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models.
arXiv AI
5d ago
A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access
The paper introduces a diagnostic protocol to disentangle the contributions of parameter sharing and neighborhood access in graph neural networks (GNNs) for electricity load forecasting. By comparing a GNN to three reference models—per-node, shared-parameter without neighbors, and the same GNN without edges—the study evaluates the impact of graph structure across datasets from France, UK feeders, and client consumption series. Results show that parameter sharing often accounts for most of the performance gain, while edges contribute less and can be diminished by degree-preserving rewiring.
arXiv Machine Learning
Aug 24
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines
arXiv:2608.20980v1 Announce Type: new Abstract: Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the...
arXiv AI
Jul 10
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
arXiv:2607. 07716v1 Announce Type: cross Abstract: Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy.