Graph Generation

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 33

All topics

Local Message-Passing for Discrete Graph Generation
Mar 9, 2026Jay Revolinsky, Harry Shomer, Jiliang TangGraph Neural Networks Graph Generation
Michigan State University East Lansing, Michigan, USA · University of Texas - Arlington Arlington, Texas, USA
Variational Bayesian Flow Network for Graph Generation
Jan 30, 2026Yida Xiong, Jiameng Chen, Xiuwen Gong +3Graph Generation Molecular Graph Generation
School of Computer Science, Wuhan University, Wuhan, China · Department of Computing, Macquarie University, Sydney, Australia · Griffith University, Gold Coast, Australia +1
Backdoor Attacks on Discrete Graph Diffusion Models
Mar 8, 2025Jiawen Wang, Samin Bin Karim, Yuan Hong +1Graph Generation Backdoor Attacks
Illinois Institute of Technology · University of Connecticut

Mar 9, 2026, cs.LGJ/K move · Enter open · S save

Local Message-Passing for Discrete Graph Generation

Jay Revolinsky, Harry Shomer, Jiliang Tang

Michigan State University East Lansing, Michigan, USA · University of Texas - Arlington Arlington, Texas, USA

Graph Neural Networks Graph Generation Message Passing Neural Networks

Open paper AskPDF arXiv

Discrete graph generation has emerged as a powerful paradigm for modeling graph-structured data, yet state of the art models often rely on Graph Transformers or higher order architectures. We revisit this design assumption by introducing GenGNN, a modular message passing backbone for graph generation. GenGNN enables powerful generation by persisting edge fields through latent refinement of coupled node edge graph states, all without requiring global attention. Diffusion models integrating GenGNN achieve over 90 percent validity on standard benchmark datasets, performing within margins of Graph Transformer backbones and achieving up to 2x or even 5x faster inference. Systematic ablations isolate how GenGNN is resilient to oversmoothing during generative denoising, indicating each GenGNN component is necessary for downstream generation quality. Finally, representation-space analysis suggests GenGNN learns functionally similar representations to more theoretically-expressive architectures; even at deeper layers. As such, GenGNN uplifts local message-passing to challenge prevailing assumptions that performant discrete graph generation requires global attention or higher-order representations. Source Code Available Here

Momentum

Related topics

Latest papers 33

Local Message-Passing for Discrete Graph Generation

Variational Bayesian Flow Network for Graph Generation

Backdoor Attacks on Discrete Graph Diffusion Models