arXiv：cs.LG· Kenneth Martin, Simon Heilig, Asja Fischer, Michel F. C. Haddad, Adam M. Sykulski, Moshe Eliasof·· 7 小时前AI 评分42
时空预测基准数据集与模型的批判性审计：GNN 性能优势被高估
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Models
AI 导读
一项对时空预测基准的审计发现，GNN 相较线性基线模型的性能优势被显著高估。研究者利用经典统计工具刻画基准中的时空滞后依赖，发现时序差分处理会改变这些关系并影响模型排名，重新评估时序线性基线后，其在多个基准上大幅缩小甚至超越了 GNN 的表现。向 GNN 提供自回归残差可提升其性能，尤其在非交通类基准上；合成实验表明 GNN 对时序动态异质性和空间图交互较为敏感。
正文
Abstract:Graph neural networks (GNNs) are routinely employed for spatiotemporal forecasting, yet their performance across widely used benchmark datasets is inconsistent. Here, we perform an audit of dataset properties and baseline models to assess the quality of the benchmarks, and the robustness of the conclusions drawn from them. Using classical statistical tools, we characterise spatiotemporal lagged dependencies in benchmarks, and examine how temporal differencing changes these relationships and affects model rankings. Motivated by this, we re-evaluate temporal linear baselines, significantly reducing the apparent gains from GNNs on several benchmarks, and surpassing GNNs on others. Suspecting that GNNs struggle to extract linear, node-wise signals, we find that supplying them with autoregressive residuals improves their performance particularly on non-traffic benchmarks. Finally, controlled synthetic experiments reveal that GNNs are sensitive to heterogeneity in temporal dynamics and spatial graph interactions. Together, our findings demonstrate that baseline specification, data pre-processing and system heterogeneity shape the interpretations drawn from benchmark rankings, informing the design and robust evaluation of GNNs.
| Subjects: | Machine Learning (cs.LG); Machine Learning (stat.ML) |
| Cite as: | arXiv:2608.20980 [cs.LG] |
| (or arXiv:2608.20980v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2608.20980 arXiv-issued DOI via DataCite |
Submission history
From: Simon Heilig [view email]
[v1]
Fri, 21 Aug 2026 11:08:17 UTC (1,822 KB)
[v2]
Tue, 6 Oct 2026 09:36:11 UTC (1,186 KB)
来源：arXiv：cs.LG · arxiv.org