DiffGraph: Controllable Graph Layout Generation with Diffusion Models
Authors
Guozheng Li (Beijing Institute of Technology), Xudong Zhou (Beijing Institute of Technology), Haotian Mi (Beijing Institute of Technology), Jinyuan Liang (Beijing Institute of Technology), Min Lu (Shenzhen University), Yi Chen (Beijing Technology and Business University), Takayuki Itoh (Ochanomizu University), Chi Harold Liu (Beijing Institute of Technology)
Presentation
- Session
- Let's dig into the data (from China)
- Time
- Friday, Nov 13, 08:00 – 08:12 (US/Eastern) · session 08:00 – 09:30
- Location
- Hall America center
Keywords
Graph, layout, constraint, diffusion model, graph neural network
Abstract
Graph visualization is an essential way to understand the relationships within graph-structured data, and node-link diagrams are widely adopted because of their intuitive representation. However, generating satisfactory layouts remains challenging, because multiple valid layouts may exist for a single graph, and their usefulness often depends on users' analytical goals. Conventional layout algorithms (e.g., force-directed methods) typically require users to tune low-level parameters to achieve desirable results, which can be time-consuming and non-intuitive for users. Recent deep learning-based methods largely operate automatically but provide limited support for expressing user intentions. We propose DiffGraph, a controllable graph layout generation method with diffusion models. DiffGraph leverages a denoising diffusion probabilistic model, with graph neural networks serving as its core architecture. Instead of requiring users to tune low-level algorithmic parameters, DiffGraph allows users to provide high-level guidance, such as relative node positions or desired global layout properties. This design enables users to incorporate domain knowledge, highlight regions of interest, or enforce specific structural patterns, thereby supporting diverse analytical needs. Qualitative and quantitative evaluations show that DiffGraph can generate high-quality and diverse layouts while effectively incorporating user-defined constraints. A user study further demonstrates that participants generally understood the constraint mechanism and perceived the generated layouts as consistent with their intentions, while an extended usage scenario illustrates how DiffGraph can support iterative and practical graph exploration.
For Practitioners
Data scientists and analysts who analyze social networks, transaction networks, citation networks, collaboration networks, communication graphs, or dependency graphs.