对比9个图模型，发现只有最新一类能超越传统神经网络。
A Fair Evaluation of Graph Foundation Models for Node Property Prediction
- 统一评估标准，重新测试9个图基础模型
- 仅最新基于先验拟合的模型性能优于优化过的GNN
- 适合关注图模型公平比较的研究者
由于图结构数据在工业和科学领域的广泛应用，图基础模型（GFMs）的开发近来受到广泛关注。尽管多种模型被称为GFMs，但针对节点属性预测任务的模型尤其受重视，该任务在图机器学习中应用广泛，涵盖金融与社交网络中的欺诈检测、电商及用户生成内容平台的推荐系统等。然而，近期提出的多个此类GFMs缺乏统一的评估标准，不同研究采用差异较大的评测方式，导致模型间难以可靠比较。本文对9个近期提出的节点属性预测用图基础模型进行了公平且严谨的重新评估，并与强基准图神经网络（GNN）进行对比。结果表明，仅有基于先验拟合网络范式的最新模型在预测性能上优于经过良好调优的GNN，尽管其推理成本更高。
原文摘要 · Abstract (English)
Due to the wide use of graph-structured data in different fields of industry and science, the development of Graph Foundation Models (GFMs) has recently attracted a lot of attention. While many different types of models are called GFMs, particular interest has been paid to GFMs designed for node property prediction tasks, which is one of the most popular settings in Graph ML with lots of real-world applications from fraud detection in financial and social networks to recommendation systems for e-commerce and user-generated content platforms. While a number of GFMs for this task have been recently proposed, the field has not converged to a unified evaluation setting, and different works evaluate their models in widely different ways, preventing reliable comparison of GFMs with each other and with other types of models. In this work, we conduct a fair and rigorous reevaluation of 9 recent GFMs for node property prediction, comparing them to strong Graph Neural Network (GNN) baselines. We find that, among these GFMs, only the most recent ones based on the Prior-data Fitted Networks paradigm outperform well-tuned GNNs in predictive performance, although at a higher inference cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。