A Network Science Perspective on Evaluating Deep Graph Generative Models

• URL: http://arxiv.org/abs/2609.01015v1
• Date: Tue, 01 Sep 2026 10:06:13 GMT
• Title: A Network Science Perspective on Evaluating Deep Graph Generative Models
• Abstract summary: Deep graph generative models learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks.<n>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.<n>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.
• Score: 1.1515813571394018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Efficient Synthetic Network Generation via Latent Embedding Reconstruction [5.202384944712403]
  We introduce Synthetic Network Generation via Latent Embedding Reconstruction (SyNGLER), a framework for synthetic network generation that builds on latent space network models.<n>SyNGLER preserves unique characteristics in networks such as sparsity and node degree heterogeneity.<n>We provide theoretical guarantees by developing consistency results on the distance between the true and synthetic edge distributions.
  arXiv  Detail & Related papers  (2026-05-31T00:01:13Z)
• Chordless cycle filtrations for dimensionality detection in complex networks via topological data analysis [2.0898985386850817]
  We introduce a novel data analysis weighting scheme for graphs, based on chordless cycles, aimed at estimating the dimensionality of networks in a data-driven way.<n>We show that the resulting descriptors can effectively estimate network dimensionality using a neural network architecture trained in a synthetic graph database.
  arXiv  Detail & Related papers  (2025-09-10T07:40:48Z)
• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Learning the mechanisms of network growth [42.1340910148224]
  We propose a novel model-selection method for dynamic networks. Data is generated by simulating nine state-of-the-art random graph models. Proposed features are easy to compute, analytically tractable, and interpretable.
  arXiv  Detail & Related papers  (2024-03-31T20:38:59Z)
• Leveraging advances in machine learning for the robust classification and interpretation of networks [0.0]
  Simulation approaches involve selecting a suitable network generative model such as Erd"os-R'enyi or small-world. We utilize advances in interpretable machine learning to classify simulated networks by our generative models based on various network attributes.
  arXiv  Detail & Related papers  (2024-03-20T00:24:23Z)
• Symbolic Regression of Dynamic Network Models [0.0]
  We introduce a novel formulation of a network generator and a parameter-free fitness function to evaluate the generated network. We extend this approach by modifying generator semantics to create and retrieve rules for time-varying networks. The framework was then used on three empirical datasets - subway networks of major cities, regions of street networks and semantic co-occurrence networks of literature in Artificial Intelligence.
  arXiv  Detail & Related papers  (2023-12-15T00:34:45Z)
• Generalization and Estimation Error Bounds for Model-based Neural Networks [78.88759757988761]
  We show that the generalization abilities of model-based networks for sparse recovery outperform those of regular ReLU networks. We derive practical design rules that allow to construct model-based networks with guaranteed high generalization.
  arXiv  Detail & Related papers  (2023-04-19T16:39:44Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks [50.684661759340145]
  Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks. We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures. In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-02-17T04:47:18Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN [16.362525151483084]
  We propose a novel dynamic heterogeneous network embedding method, termed as DyHATR. It uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction.
  arXiv  Detail & Related papers  (2020-04-01T17:16:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.