Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation

• URL: http://arxiv.org/abs/2603.23398v1
• Date: Tue, 24 Mar 2026 16:35:25 GMT
• Title: Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation
• Abstract summary: Graph Energy Matching (GEM) is a generative framework for graphs that closes the fidelity gap between discrete diffusion models and energy-based models.<n>GEM learns a permutation-invariant potential energy that simultaneously provides transport-aligned guidance from noise toward data and refines samples within regions of high data likelihood.<n>Beyond sample quality, explicit modeling of relative likelihood enables targeted exploration at inference time, facilitating compositional generation, property-constrained sampling, and geodesic between graphs.
• Score: 39.944645380380926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Energy-based models for discrete domains, such as graphs, explicitly capture relative likelihoods, naturally enabling composable probabilistic inference tasks like conditional generation or enforcing constraints at test-time. However, discrete energy-based models typically struggle with efficient and high-quality sampling, as off-support regions often contain spurious local minima, trapping samplers and causing training instabilities. This has historically resulted in a fidelity gap relative to discrete diffusion models. We introduce Graph Energy Matching (GEM), a generative framework for graphs that closes this fidelity gap. Motivated by the transport map optimization perspective of the Jordan-Kinderlehrer-Otto (JKO) scheme, GEM learns a permutation-invariant potential energy that simultaneously provides transport-aligned guidance from noise toward data and refines samples within regions of high data likelihood. Further, we introduce a sampling protocol that leverages an energy-based switch to seamlessly bridge: (i) rapid, gradient-guided transport toward high-probability regions to (ii) a mixing regime for exploration of the learned graph distribution. On molecular graph benchmarks, GEM matches or exceeds strong discrete diffusion baselines. Beyond sample quality, explicit modeling of relative likelihood enables targeted exploration at inference time, facilitating compositional generation, property-constrained sampling, and geodesic interpolation between graphs.

Related papers

• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• Energy-Guided Flow Matching Enables Few-Step Conformer Generation and Ground-State Identification [45.52894539097255]
  We present EnFlow, a unified framework that couples flow matching with an explicitly learned energy model.<n>By incorporating energy-gradient guidance during sampling, our method steers trajectories toward lower-energy regions.<n>The learned energy function further enables efficient energy-based ranking of generated ensembles for accurate ground-state identification.
  arXiv  Detail & Related papers  (2025-12-27T14:00:22Z)
• Discrete Bayesian Sample Inference for Graph Generation [48.418206985863726]
  We introduce GraphBSI, a novel one-shot graph generative model based on Bayesian Sample Inference (BSI)<n>We state BSI as a differential equation (SDE) and derive a noise-controlled family of SDEs that preserves the marginal distributions via an approximation of the score function.<n>In our empirical evaluation, we demonstrate state-of-the-art performance on molecular and synthetic graph generation, outperforming existing one-shot graph generative models.
  arXiv  Detail & Related papers  (2025-11-04T21:25:51Z)
• Bures-Wasserstein Flow Matching for Graph Generation [10.21877898746333]
  We present a theoretically grounded framework for probability path construction in graph generative models.<n>We then leverage the optimal transport displacement between MRF objects to design a smooth probability path.<n> BWFlow is a flow-matching framework for graph generation that utilizes the derived optimal probability path.
  arXiv  Detail & Related papers  (2025-06-16T21:36:56Z)
• Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling [5.787270247104665]
  Current state-of-the-art generative models map noise to data distributions by matching flows or scores.<n>Here, we propose Energy Matching, a framework that endows flow-based approaches with the flexibility of EBMs.
  arXiv  Detail & Related papers  (2025-04-14T18:10:58Z)
• Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs [61.226857589092]
  OOD detection on nodes in graph learning remains underexplored.<n>GNNSafe adapted energy-based detection to the graph domain with state-of-the-art performance.<n>We introduce DeGEM, which decomposes the learning process into two parts: a graph encoder that leverages topology information for node representations and an energy head that operates in latent space.
  arXiv  Detail & Related papers  (2025-02-25T07:20:00Z)
• DeFoG: Discrete Flow Matching for Graph Generation [45.037260759871124]
  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.
  arXiv  Detail & Related papers  (2024-10-05T18:52:54Z)
• Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling [10.926841288976684]
  We present a novel energy-based generative framework, Variational Potential Flow (VAPO) VAPO aims to learn a potential energy function whose gradient (flow) guides the prior samples, so that their density evolution closely follows an approximate data likelihood homotopy. Images can be generated after training the potential energy, by initializing the samples from Gaussian prior and solving the ODE governing the potential flow on a fixed time interval.
  arXiv  Detail & Related papers  (2024-07-21T18:08:12Z)
• 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.