arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.18524cs.LG
收藏

增强特征的图神经网络用于合成图生成模型分类:基准研究

Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study

Abertay University(阿伯塔伊大学)

Janek Dyer, Jagdeep Ahluwalia, Javad Zarrin

AI总结:

本文提出了一种结合图神经网络与人工设计图论特征的方法,用于合成图生成模型的分类任务,发现GraphSAGE和GTN在分类性能上表现最佳。

摘要:

区分生成图模型的能力对于理解合成图和它们所模拟的现实结构中的复杂结构模式至关重要。尽管图神经网络(GNNs)在图分类任务中得到了广泛应用,但很少有研究探讨其与可解释的图论特征的结合。本文研究了使用混合方法对合成图家族进行分类,该方法结合了GNNs和人工设计的图论特征。我们生成了一个大规模且结构多样的合成数据集,包含来自五个代表性生成家族的图:Erdos-Renyi、Watts-Strogatz、Barab'asi-Albert、Holme-Kim和Stochastic Block Model。这些图的节点数最多达到1x10^4,边数最多达到1.1x10^5。每个图都提取了广泛范围的节点和图级特征,并通过基于随机森林的特征选择管道进行修剪。这些特征被整合到六个GNN架构中:GCN、GAT、GATv2、GIN、GraphSAGE和GTN。每个架构都通过Optuna进行超参数优化。最后,模型与仅基于人工特征训练的基线支持向量机(SVM)进行比较。我们的评估表明,GraphSAGE和GTN实现了最高的分类性能,准确率达到98.5%,t-SNE和UMAP可视化显示了良好的类别分离。GCN和GIN也表现良好,而基于GAT的模型由于在捕捉全局结构方面的局限而表现较差。SVM基线确认了信息传递功能对性能提升和有意义类别分离的重要性。

英文摘要:

The ability to discriminate between generative graph models is critical to understanding complex structural patterns in both synthetic graphs and the real-world structures that they emulate. While Graph Neural Networks (GNNs) have seen increasing use to great effect in graph classification tasks, few studies explore their integration with interpretable graph theoretic features. This paper investigates the classification of synthetic graph families using a hybrid approach that combines GNNs with engineered graph-theoretic features. We generate a large and structurally diverse synthetic dataset comprising graphs from five representative generative families, Erdos-Renyi, Watts-Strogatz, Barab'asi-Albert, Holme-Kim, and Stochastic Block Model. These graphs range in size up to 1x10^4 nodes, containing up to 1.1x10^5 edges. A comprehensive range of node and graph level features is extracted for each graph and pruned using a Random Forest based feature selection pipeline. The features are integrated into six GNN architectures: GCN, GAT, GATv2, GIN, GraphSAGE and GTN. Each architecture is optimised for hyperparameter selection using Optuna. Finally, models were compared against a baseline Support Vector Machine (SVM) trained solely on the handcrafted features. Our evaluation demonstrates that GraphSAGE and GTN achieve the highest classification performance, with 98.5% accuracy, and strong class separation evidenced by t-SNE and UMAP visualisations. GCN and GIN also performed well, while GAT-based models lagged due to limitations in their ability to capture global structures. The SVM baseline confirmed the importance of the message passing functionality for performance gains and meaningful class separation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑