CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xi, Gongli, Tian, Ye, Yang, Mengyu, Zhao, Zhenyu, Zhang, Yuchao, Gong, Xiangyang, Que, Xirong, Wang, Wendong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915691477598208
author Xi, Gongli
Tian, Ye
Yang, Mengyu
Zhao, Zhenyu
Zhang, Yuchao
Gong, Xiangyang
Que, Xirong
Wang, Wendong
author_facet Xi, Gongli
Tian, Ye
Yang, Mengyu
Zhao, Zhenyu
Zhang, Yuchao
Gong, Xiangyang
Que, Xirong
Wang, Wendong
contents The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph-level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology
Xi, Gongli
Tian, Ye
Yang, Mengyu
Zhao, Zhenyu
Zhang, Yuchao
Gong, Xiangyang
Que, Xirong
Wang, Wendong
Machine Learning
Artificial Intelligence
The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph-level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset.
title CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.19736