From topology learning to graph generation: A unifying perspective
Abstract
Learning graph structures from data is a fundamental problem that spans a wide range of signal processing and machine learning tasks. While significant effort has been made to tackle the problem, existing research has largely evolved along two parallel directions. The first seeks to infer the topology of an individual graph from observations supported on it, whereas the second seeks to learn a generative distribution from observed graph instances, enabling the sampling of new graphs. This review presents a unified framework that connects these formulations by viewing them as inverse problems of a common generation process for graph data. We review the major methodologies within this framework, highlight their relationships, strengths, and limitations, and identify opportunities for integrating ideas across paradigms. By bridging graph topology learning and graph generation, this review provides a broader cross-disciplinary perspective on the field and outlines promising directions for future research.
Related
- Adaptive Task Offloading Under Dynamic Topology via Graph Attention-Enhanced Reinforcement Learning for Layered UAV-Enabled Digital Twin Channel Modeling
- Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning
- A Unifying Perspective on Probabilities as Model Predictions
- Explainable spatiotemporal Graph Neural Networks: Multi-City PM2.5 forecasting in Bangladesh with geographic graph topology validation
- Graph Additive Models disentangling feature, topology, and interactions
BibTeX
@misc{dong2026from,
title = {{From topology learning to graph generation: A unifying perspective}},
author = {Xiaowen Dong and Hoi-To Wai and Siheng Chen and Laura Toni and Dorina Thanou},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.02286},
eprint = {2609.02286},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.02286},
}
RIS
TY - UNPB
TI - From topology learning to graph generation: A unifying perspective
AU - Xiaowen Dong
AU - Hoi-To Wai
AU - Siheng Chen
AU - Laura Toni
AU - Dorina Thanou
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2609.02286
UR - https://arxiv.org/abs/2609.02286
AB - Learning graph structures from data is a fundamental problem that spans a wide range of signal processing and machine learning tasks. While significant effort has been made to tackle the problem, existing research has largely evolved along two parallel directions. The first seeks to infer the topology of an individual graph from observations supported on it, whereas the second seeks to learn a generative distribution from observed graph instances, enabling the sampling of new graphs. This review presents a unified framework that connects these formulations by viewing them as inverse problems of a common generation process for graph data. We review the major methodologies within this framework, highlight their relationships, strengths, and limitations, and identify opportunities for integrating ideas across paradigms. By bridging graph topology learning and graph generation, this review provides a broader cross-disciplinary perspective on the field and outlines promising directions for future research.
ER -