发表机构
Nums AI（Nums AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NodeGround基准在51个数据集上统一评估图基础模型与监督方法，发现精心调优的GNN总体更优，预训练复用尚不能广泛提供更强预测或更低成本。
AI 中文摘要
预训练图模型能否取代为每个数据集单独训练和调优预测器？回答这个问题需要同时评估预测质量和计算成本。我们提出了NodeGround，一个节点分类基准，将图基础模型（GFMs）和特定数据集的监督学习置于统一的评估框架下。该基准涵盖51个数据集，在两种标签可用性设置下评估了六种GFMs和15种监督方法。共享的数据划分、仅验证集模型选择、受控的超参数搜索以及多种预测指标使比较系统化，而工作流测量则考虑了适应、训练、调优和推理。总体结果倾向于精心调优的图神经网络。当更多标签可用时，GraphPFN在Elo排名中达到第三位，但其相对优势随数据集属性变化显著。效率比较进一步限定了预训练复用的好处：当监督方法以其默认和完全调优配置表示时，GVT和GraphPFN出现在帕累托前沿上。增加中间调优预算消除了GVT的这一优势，仅留下GraphPFN在标签丰富设置中扩展估计的前沿。因此，复用预训练参数尚未为更强的预测或更便宜的工作流提供广泛可靠的途径。我们在https URL发布了评估流程、运行级记录和开放排行榜。
英文摘要
Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality alongside computational cost. We present NodeGround, a node classification benchmark that puts graph foundation models (GFMs) and dataset-specific supervised learning under a common evaluation framework. The benchmark spans 51 datasets and evaluates six GFMs alongside 15 supervised methods under two label-availability regimes. Shared data partitions, validation-only model selection, controlled hyperparameter searches, and multiple predictive metrics make comparisons systematic, while workflow measurements account for adaptation, training, tuning, and inference. The results favor carefully tuned graph neural networks overall. GraphPFN reaches third place by Elo when more labels are available, yet its relative strengths vary substantially with dataset properties. Efficiency comparisons further qualify the benefits of pretrained reuse: GVT and GraphPFN appear on the Pareto frontiers when supervised methods are represented by their default and fully tuned configurations. Adding intermediate tuning budgets removes this advantage for GVT and leaves GraphPFN extending the estimated frontier in the label-rich setting alone. Thus, reusing pretrained parameters does not yet provide a broadly reliable route to either stronger predictions or cheaper workflows. We release the evaluation pipeline, run-level records, and an open leaderboard at https://github.com/nums-ai/nodeground.
