发表机构
Wrocław University of Science and Technology; University of Technology Sydney; SGH Warsaw School of Economics; Toronto Metropolitan University（弗罗茨瓦夫理工大学; 悉尼科技大学; 华沙经济大学; 多伦多都会大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DCBA，一种基于模型的反演图生成器配置的图数据增强方法，通过多正对比学习联合表示图与生成器参数，恢复ABCD配置以保留宏观结构，并在社区检测中显著提升AMI性能。
AI 中文摘要
图是许多复杂系统的自然表示，范围从社交平台到生态系统。然而，基于图的机器学习方法的发展常常受到大型且多样化的图数据集可用性有限的制约。在本文中，我们介绍了$\ exttt{DCBA}$，一种基于模型的图数据增强方法，该方法从观测网络中推断合成图生成器的配置。我们使用$\ exttt{ABCD}$生成器实例化所提出的框架，该生成器生成具有社区结构的无标度网络。我们的模型使用具有软负加权的多正对比目标学习图和生成器参数的联合表示。学习到的表示能够预测$\ exttt{ABCD}$配置，其随机实现保留了生成器编码的宏观结构属性。实验表明，$\ exttt{DCBA}$比算法逆建模基线更准确、更稳健地恢复生成器参数。其下游效用进一步在社区检测中得到证明，其中用于微调$\ exttt{PRoCD}$的推断配置在合成网络上平均提高了$161\%$的AMI，在真实世界网络上平均提高了$273\%$。
英文摘要
Graphs provide a natural representation of many complex systems, ranging from social platforms to ecosystems. However, the development of graph-based machine learning methods is often constrained by the limited availability of large and diverse graph datasets. In this paper, we introduce $\texttt{DCBA}$, a model-based approach to graph data augmentation that infers the configuration of a synthetic graph generator from an observed network. We instantiate the proposed framework using the $\texttt{ABCD}$ generator, which produces scale-free networks with community structure. Our model learns a joint representation of graphs and generator parametrisations using a multi-positive contrastive objective with soft negative weighting. The learned representation enables the prediction of an $\texttt{ABCD}$ configuration whose stochastic realisations preserve the macrostructural properties encoded by the generator. Experiments show that $\texttt{DCBA}$ recovers generator parameters more accurately and robustly than an algorithmic inverse-modelling baseline. Its downstream utility is further demonstrated in community detection, where inferred configurations used to fine-tune $\texttt{PRoCD}$ improve AMI on average by $161\%$ on synthetic and $273\%$ on real-world networks.
CommentsAccepted to 5th Learning on Graphs Conference; Boston, MA, USA; 20-22.11.2026
