SynCo：用于图神经网络基准测试的合成社区感知属性图生成器
SynCo: Synthetic Community-Aware Attributed Graph Generator for Graph Neural Network Benchmarking
浏览论文内容
中文总结 AI 辅助
SynCo是一种社区感知的属性图生成器，允许用户控制度分布和子社区结构，在图模仿、超参数评估和节点聚类任务中优于现有方法，并能生成多达210万节点的大规模图。
中文摘要 AI 辅助
图神经网络（GNN）是处理属性图（如分类、链接预测和社区检测等任务）的强大模型，因为它们能够聚合来自结构和语义来源的信息。然而，社区检测的进展受到缺乏高质量数据集的阻碍，因为真实社区标签通常不可用，且近期文献中提出的大多数算法依赖于相同的基准数据集进行模型训练和评估。为解决此问题，属性随机图生成器通常被用来创建合成图，以评估基于GNN的模型的优缺点。尽管如此，大多数现有生成器严重依赖幂律度分布，尽管近期证据表明无标度网络很少见，尤其是在社交网络背景下。此外，最先进的属性图生成器提供的灵活性有限，因为它们不允许用户构建具有不同密度、度分布和子社区结构的社区。为克服这些限制，我们引入了合成社区感知属性图生成器（SynCo），这是一种图生成算法，允许用户控制节点度分布和子社区结构。我们在三个不同任务上评估SynCo：图模仿、超参数评估和节点聚类调优。结果表明，我们的模型在合成图生成和数据增强方面优于最先进的方法，同时保留了复制和增强数据集的原始分布，这通过文献中众所周知的统计检验得到证实。我们还展示了SynCo生成大规模节点的能力，最多可达210万个节点。
英文摘要
Graph Neural Networks (GNNs) are powerful models for handling attributed graphs in tasks such as classification, link prediction, and community detection, as they enable the aggregation of information from both structural and semantic sources. However, progress in community detection is hindered by the lack of high-quality datasets, since ground-truth community labels are often unavailable and most algorithms proposed in recent literature rely on the same benchmark datasets for model training and evaluation. To address this issue, attributed random graph generators are commonly employed to create synthetic graphs for assessing the strengths and limitations of GNN-based models. Nevertheless, most existing generators rely heavily on power-law degree distributions, despite recent evidence indicating that scale-free networks are rare, particularly in social network contexts. Moreover, state-of-the-art attributed graph generators provide limited flexibility, as they do not allow users to construct communities with varying densities, degree distributions, and sub-community structures. To overcome these limitations, we introduce the Synthetic Community-Aware Attributed Graph Generator (SynCo), a graph generation algorithm that allows users to control the node degree distribution and sub-community structure. We evaluate SynCo across three different tasks: graph mimicking, hyperparameter evaluation, and node clustering tuning. The results show that our model outperforms state-of-the-art approaches in synthetic graph generation and data augmentation, while preserving the original distributions of duplicated and augmented datasets, as confirmed by statistical tests well know in literature. We also demonstrate the ability of SynCo to generate nodes in large scale, up to 2.1 million nodes.
发表机构
- Federal University of São Carlos（圣卡洛斯联邦大学）
- Federal University of Mato Grosso do Sul（南马托格罗索联邦大学）
机构由 AI 辅助整理，请以论文原文为准。
