GraphToolbox is presented, an open-source Python framework that unifies graph construction, model selection, training, aggregation, and interpretation in one configurationdriven pipeline built on PyTorch Geometric.
Abstract
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.
Timely and effective weather predictions are important for managing climate-related phenomena, disasters, and risks; for agriculture and aviation; and for making informed decisions in regard to the environment. Existing weather prediction systems have great difficulty addressing the needs for understanding the complex...
Koteswararao B, R. Krishnamoorthi· 2026 International Conferenc...· 0 citations
Graphs are widely used to describe objects and their interactions in physically-informed real-world networking scenario including transportation, networking and energy, etc. Graph neural network (GNN) is the latest deep learning (DL) model for processing graph-structured data, widely applied in various tasks, e.g., p...
Yu-Feng Wang, Xin-Ying-Jian-Gan-Zhi-De-Shen-Jing-Jia-Gou-Sou-Suo Wang, Jian-Hua Ma et al.· Artificial Intelligence Revi...· 0 citations
Multivariate long-sequence time series forecasting (MLSTF) is critical in applications such as electricity consumption planning, where accurate prediction requires models to capture complex temporal dependencies over extended horizons while remaining computationally efficient. Current MLSTF methods are largely built up...
Zhi-Yuan Zuo, Zhao-Ming Tian, Xiao-Yu Cao et al.· 2026 IEEE 22nd International...· 0 citations
DeltaGNN is introduced, to the best of the authors' knowledge, among the first scalable (featuring linear computational and memory complexity overhead) and generalizable (capable of effectively handling graphs with diverse homophily, density, and topology) architectures for long-range and short-range interaction detect...
Kevin Mancini, Islem Rekik· IEEE Transactions on Pattern...· 2 citations
Graph neural networks (GNNs) are a class of neural networks suitable for learning on graph-structured data. Their application to spatial data is a natural extension, however its relatively unclear which message-passing operations, architectural configurations, and graph representation is best suited for classifying cha...
Accurate bus Estimated Time of Arrival (ETA) prediction is vital for urban mobility, passenger satisfaction, and transit efficiency, yet existing models falter against nonlinear spatiotemporal dynamics, data sparsity, and factors such as weather. This paper proposes HYB(nm), an adaptive hybrid ensemble framework that d...
Pratham Payra, Jagadish· arXiv.org· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.