arXiv：cs.AI· Tianrui Mao, Abele Malan, Megha Khosla, Lydia Chen, Huijuan Wang·· 3 小时前
从网络科学视角评估深度图生成模型
A Network Science Perspective on Evaluating Deep Graph Generative Models
AI 导读
研究从网络科学视角评估深度图生成模型与传统 configuration 模型，比较生成网络与真实网络的结构相似性及其识别有效节点免疫策略的能力。结果显示，两个深度图生成模型生成的合成网络在结构属性上接近真实网络，并能据此识别有效的免疫策略。合成网络可替代因隐私风险无法共享的真实社会接触网络，用于流行病与虚假信息传播防控策略的评估。
正文
Abstract:Traditional network models from network science, such as the Erdos-Renyi and configuration models, generate random networks that reproduce few selected topological properties observed in real-world networks. Deep graph generative models emerge as a data-driven approach, leveraging deep neural network architectures to learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks. Because real social contact networks cannot be shared due to privacy risks, synthetic networks serve as an alternative for developing and evaluating epidemic mitigation strategies. In this work, we evaluate deep graph generative models as well as the configuration from a network science perspective by assessing both the topological similarity between generated and real-world networks and their utility in identifying effective node immunization strategies to sup- press epidemic/misinformation spreading. It is found that two deep graph generative models produce synthetic networks that closely resemble the structural properties of real-world networks, enabling them to identify effective immunization strategies.
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.01015 [cs.SI] |
| (or arXiv:2609.01015v2 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.01015 arXiv-issued DOI via DataCite |
Submission history
From: Tianrui Mao [view email]
[v1]
Tue, 1 Sep 2026 10:06:13 UTC (3,897 KB)
[v2]
Thu, 8 Oct 2026 14:45:50 UTC (10,180 KB)
来源：arXiv：cs.AI · arxiv.org