DeFoG: Discrete Flow Matching for Graph Generation

• URL: http://arxiv.org/abs/2410.04263v2
• Date: Fri, 07 Mar 2025 12:18:32 GMT
• Title: DeFoG: Discrete Flow Matching for Graph Generation
• Authors: Yiming Qin, Manuel Madeira, Dorina Thanou, Pascal Frossard,
• Abstract summary: We introduce DeFoG, a graph generative framework that disentangles sampling from training.<n>We propose novel sampling methods that significantly enhance performance and reduce the required number of refinement steps.
• Score: 45.037260759871124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited flexibility due to the tight coupling between training and sampling stages. We introduce DeFoG, a novel graph generative framework that disentangles sampling from training, enabling a broader design space for more effective and efficient model optimization. DeFoG employs a discrete flow-matching formulation that respects the inherent symmetries of graphs. We theoretically ground this disentangled formulation by explicitly relating the training loss to the sampling algorithm and showing that DeFoG faithfully replicates the ground truth graph distribution. Building on these foundations, we thoroughly investigate DeFoG's design space and propose novel sampling methods that significantly enhance performance and reduce the required number of refinement steps. Extensive experiments demonstrate state-of-the-art performance across synthetic, molecular, and digital pathology datasets, covering both unconditional and conditional generation settings. It also outperforms most diffusion-based models with just 5-10% of their sampling steps.

Related papers

• Surrogate models for diffusion on graphs via sparse polynomials [0.40964539027092906]
  We provide sparse-based surrogate models for parametric diffusion equations on graphs with community structure. Our theoretical findings are accompanied by a series of numerical experiments conducted on both synthetic and real-world graphs.
  arXiv  Detail & Related papers  (2025-02-10T15:57:33Z)
• Cometh: A continuous-time discrete-state graph diffusion model [8.444907767842228]
  We propose Cometh, a continuous-time discrete-state graph diffusion model, tailored to the specificities of graph data. In terms of VUN samples, Cometh obtains a near-perfect performance of 99.5% on the planar graph dataset and outperforms DiGress by 12.6% on the large GuacaMol dataset.
  arXiv  Detail & Related papers  (2024-06-10T16:39:39Z)
• Fisher Flow Matching for Generative Modeling over Discrete Data [12.69975914345141]
  We introduce Fisher-Flow, a novel flow-matching model for discrete data. Fisher-Flow takes a manifestly geometric perspective by considering categorical distributions over discrete data. We prove that the gradient flow induced by Fisher-Flow is optimal in reducing the forward KL divergence.
  arXiv  Detail & Related papers  (2024-05-23T15:02:11Z)
• Discrete-state Continuous-time Diffusion for Graph Generation [46.626952802292074]
  Diffusion generative models have been applied to graph generation tasks. We formulate the graph diffusion generation in a discrete-state continuous-time setting. Our proposed model shows competitive empirical performance against state-of-the-art graph generation solutions.
  arXiv  Detail & Related papers  (2024-05-19T00:09:42Z)
• Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory [87.00653989457834]
  Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. Despite the empirical success, theory of conditional diffusion models is largely missing. This paper bridges the gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models.
  arXiv  Detail & Related papers  (2024-03-18T17:08:24Z)
• Distribution-Aware Data Expansion with Diffusion Models [55.979857976023695]
  We propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model. DistDiff consistently enhances accuracy across a diverse range of datasets compared to models trained solely on original data.
  arXiv  Detail & Related papers  (2024-03-11T14:07:53Z)
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution [67.9215891673174]
  We propose score entropy as a novel loss that naturally extends score matching to discrete spaces. We test our Score Entropy Discrete Diffusion models on standard language modeling tasks.
  arXiv  Detail & Related papers  (2023-10-25T17:59:12Z)
• Graph Out-of-Distribution Generalization with Controllable Data Augmentation [51.17476258673232]
  Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. Due to the selection bias of training and testing data, distribution deviation is widespread. We propose OOD calibration to measure the distribution deviation of virtual samples.
  arXiv  Detail & Related papers  (2023-08-16T13:10:27Z)
• SaGess: Sampling Graph Denoising Diffusion Model for Scalable Graph Generation [7.66297856898883]
  SaGess is able to generate large real-world networks by augmenting a diffusion model (DiGress) with a generalized divide-and-conquer framework. SaGess outperforms most of the one-shot state-of-the-art graph generating methods by a significant factor.
  arXiv  Detail & Related papers  (2023-06-29T10:02:39Z)
• Directional diffusion models for graph representation learning [9.457273750874357]
  We propose a new class of models called it directional diffusion models These models incorporate data-dependent, anisotropic, and directional noises in the forward diffusion process. We conduct extensive experiments on 12 publicly available datasets, focusing on two distinct graph representation learning tasks.
  arXiv  Detail & Related papers  (2023-06-22T21:27:48Z)
• Fast Graph Generative Model via Spectral Diffusion [38.31052833073743]
  We argue that running full-rank diffusion SDEs on the whole space hinders diffusion models from learning graph topology generation. We propose an efficient yet effective Graph Spectral Diffusion Model (GSDM), which is driven by low-rank diffusion SDEs on the graph spectrum space.
  arXiv  Detail & Related papers  (2022-11-16T12:56:32Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.