arXiv cs.AI· Eloi Campagne (CB), Yvenn Amara-Ouali (LMO), Yannig Goude (LMO), Itai Zehavi (CB), Argyris Kalogeratos (CB)·· 15 小时前AI 评分29
用于电力负荷预测 GNN 的诊断协议：区分参数共享与邻域访问
A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access
AI 导读
研究者提出一套 GNN 诊断协议，通过与逐节点网络、无邻居共享网络及去边 GNN 三个参考模型对比，区分参数共享与邻域访问各自的贡献。在法国区域负荷和英国低压馈线数据上，参数共享在馈线上挽回了约三分之二的误差差距，而加边带来的增益有一半以上在度保持重连后消失。三个数据集中边均未构成 GNN 相对逐节点模型优势的主要来源，预测增益需在与逐节点及共享参考对比后才能归因于图结构。
正文 · 原文
Abstract:A graph neural network (GNN) forecasting a collection of load series combines two mechanisms, sharing parameters across series and reading neighboring series, and a gain over a non-graph model may come from either; telling them apart decides whether a graph is worth maintaining. We propose a model diagnostic protocol that compares the GNN with three reference models: a per-node network, a network shared across nodes without neighbors, and the same GNN without edges. Degree-preserving rewiring tests whether neighbor identity matters. After a tuned benchmark on regional load in France and on low-voltage feeders in the UK, we apply the protocol to deliberately short node histories, as when non-stationary demand leaves only recent observations relevant: the feeders, within one week, and a public dataset of client consumption series. On the feeders, sharing parameters recovers most of the error gap between node-specific models and GNNs, about two thirds against a regularized one. Adding the edges to an otherwise identical backbone brings a smaller gain, half or more of which disappears under rewiring. On the client series, the neighbor mean degrades the per-node model on the shorter window and the edges' gain is not consistently distinguishable from zero; on the regions of France, where each node's own history is already informative, the ranking between per-node models and GNNs changes with tuning. A synthetic study points to noisy local measurements as one regime where neighbors help. In an exploratory online aggregation, graph and non-graph forecasters appear complementary, and the weight assigned to GNNs is not proportional to their contribution. In none of the three datasets do the edges account for most of a GNN's advantage over node-specific models, so a forecasting gain should be credited to the graph only after comparison with per-node and shared references.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35074 [cs.AI] |
| (or arXiv:2610.35074v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35074 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Eloi Campagne [view email] [via CCSD proxy]
[v1]
Mon, 26 Oct 2026 09:20:23 UTC (2,015 KB)
来源：arXiv cs.AI · arxiv.org