Metraipolis › archive › dc_cc8c07321dfb

GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting — arXiv:2609.24609

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24609
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:51.801Z
SHA-256 of the archived text
da4896b6b1ceef7440f599aeb439d01407a1ff9707429268106d62998fa55771
Stable URL of this page
https://metraipolis.com/documento/dc_cc8c07321dfb

How to cite

GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting — arXiv:2609.24609 — arXiv (en), https://arxiv.org/abs/2609.24609 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc8c07321dfb (Metraipolis archive dc_cc8c07321dfb, sha256 da4896b6b1ceef7440f599aeb439d01407a1ff9707429268106d62998fa55771)
BibTeX
@misc{dccc8c07321dfb,
  title = {GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting — arXiv:2609.24609},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24609},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc8c07321dfb; sha256 da4896b6b1ceef7440f599aeb439d01407a1ff9707429268106d62998fa55771},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24609. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) provide a natural way to represent these relations. Building a complete GNN forecasting experiment is nonetheless laborious, because graph construction, model selection, training, aggregation, and interpretation sit in incompatible tools. We present GraphToolbox, an open-source Python framework that unifies these stages in one configurationdriven pipeline built on PyTorch Geometric. It offers data-driven graph construction, an adapter that instantiates and trains 51 of the 65 PyTorch Geometric convolutions together with the recurrent cells of PyTorch Geometric Temporal, online expert aggregation, forecasting interpretability, and significance testing on cached forecasts. We evaluate the pipeline in two case studies. On French regional load, the 48 convolutions included in the complete forecasting sweep fall in a band from 1.14% to 1.60% error, online aggregation lowers this to 0.98%, and the graph models improve on classical additive and boosting baselines. On net-load, direct graph models are less accurate than a classical additive model, while forecasting each physical component separately improves them without closing that gap. Both comparisons use the same experimental interface, illustrating the role of GraphToolbox in systematic architectural evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24609 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.434Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).