Graph Generation

Ask about this topic

Overview

Graph generation studies how to create networks whose nodes, edges, and attributes reproduce useful patterns or meet specified constraints, supporting tasks such as molecule design, network simulation, and structured data synthesis. Common approaches include autoregressive models that add nodes or edges sequentially, diffusion and flow-matching models that denoise or transform graphs, and latent-variable, graphon, reinforcement-learning, and evolutionary methods. Models are evaluated on synthetic networks, molecular benchmarks, and application-specific graphs for structural fidelity, validity, diversity, novelty, and computational cost. A central challenge is scaling to large or variable-size graphs while balancing distributional accuracy and novelty with hard constraints, controllability, and protection against memorization or bias.

Latest papers

CardsList

69 papers18 papers in the last four weeks, up 125% on the four weeks before. 0.1% of all new papers.

  1. Local Message-Passing for Discrete Graph Generation

    Mar 9, 2026Jay Revolinsky, Harry Shomer, Jiliang TangGraph Neural NetworksGraph Generation

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

  2. Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

    Mar 2, 2026Wendi Wang, Jiaxi Yang, Yongkang Du +1Graph GenerationGraph Diffusion

    Purdue University · Pennsylvania State University

  3. CARD: Towards Conditional Design of Multi-agent Topological Structures

    Mar 1, 2026Tongtong Wu, Yanming Li, Ziye Tang +5Multi-Agent LLM SystemsMulti-Agent Communication

    Monash University · Southeast University · Griffith University

  4. Flowette: Flow Matching with Graphette Priors for Graph Generation

    Feb 27, 2026Asiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M. Steinberg +1Graph GenerationFlow-Based Generative Modeling

    CSIRO’s Data61 · Australian National University

  5. DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

    Feb 22, 2026Aleksei Liuliakov, Luca Hermes, Barbara HammerGraph GenerationGraph Diffusion

    Machine Learning Group, Bielefeld University, Germany

  6. Investigating GNN Convergence on Large Randomly Generated Graphs with Realistic Node Feature Correlations

    Feb 18, 2026Mohammed Zain Ali AhmedGraph Neural NetworksGNN Expressivity

  7. Variational Bayesian Flow Network for Graph Generation

    Jan 30, 2026Yida Xiong, Jiameng Chen, Xiuwen Gong +3Graph GenerationMolecular Graph Generation

    School of Computer Science, Wuhan University, Wuhan, China · Department of Computing, Macquarie University, Sydney, Australia · Griffith University, Gold Coast, Australia +1

  8. Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networks

    Jan 28, 2026Alexandre Larouche, Audrey DurandGenerative Flow NetworksGraph Generation

    D´epartement d’informatique et de g´enie logiciel, Universit´e Laval, Qu´ebec, Canada · Mila - Quebec AI Institute, Montr´eal, Canada · Canada CIFAR AI Chair

  9. Backdoor Attacks on Discrete Graph Diffusion Models

    Mar 8, 2025Jiawen Wang, Samin Bin Karim, Yuan Hong +1Graph GenerationBackdoor Attacks

    Department of Computer Science, Illinois Institute of Technology · School of Computing, University of Connecticut