mlsanityData to 14 Oct 2026

Data Enrichment for Symbolic Regression Using Diffusion Models

arXiv 2606.00988 ↗First posted 31 May 2026cs.LGcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Symbolic regression (SR) offers a route to scientific discovery by converting observations into interpretable governing equations. However, despite its promise, its reliability degrades sharply when spatiotemporal measurements are sparse, noisy, or physically incomplete, as commonly occurring in practice. Data enrichment (DE) has been shown to be able to mitigate this limitation, yet additional samples can mislead equation discovery unless they preserve the physical structure of the target system. Such implication of DE requires narrow domain expertise as well as technical fluidity, highly limiting its practical usefulness. In this study, we introduce a physics-guided latent diffusion framework for DE for down the line SR models. The proposed framework combines a variational autoencoder, a conditional latent diffusion model, and a physics-informed residual corrector to complete sparse observations with synthetic fields constrained by governing relations. We evaluate the approach on heat conduction, incompressible Navier-Stokes flow, and a moving single-mass Newtonian gravitational potential, using GPLearn, DEAP, and PySR as downstream SR backends. Our results reveal that physics-corrected enrichment consistently improves recovery in sparse regimes across physical dynamics and SR models. These results show that generative enrichment can strengthen equation discovery without additional domain expertise.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 61 of its 116 references that are in the map. First posted on arXiv 31 May 2026.

Builds on

61 of 116 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observation25 Jun
  2. 2024Physics-Informed Diffusion Models21 Mar
  3. 2023Bayesian Conditional Diffusion Models for Versatile Spatiotemporal Turbulence Generation14 Nov
  4. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction26 Nov

Other references · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
38 more
  1. 2022Video Diffusion Modelscited by 2,305
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  4. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  5. 2022Denoising Diffusion Restoration Modelscited by 963
  6. 2017DGM: A deep learning algorithm for solving partial differential equationscited by 678
  7. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  8. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
  9. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  10. 2021Neural Operator: Learning Maps Between Function Spacescited by 414
  11. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 344
  12. 2020B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Datacited by 335
  13. 2019Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradientscited by 309
  14. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  15. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 294
  16. 2022A Survey on Generative Diffusion Modelcited by 240
  17. 2021Contemporary Symbolic Regression Methods and their Relative Performancecited by 215
  18. 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 210
  19. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
  20. 2016Theory-guided Data Science: A New Paradigm for Scientific Discovery from Datacited by 171
  21. 2021Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and controlcited by 137
  22. 2020SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear Dynamicscited by 125
  23. 2022Interpretable Scientific Discovery with Symbolic Regression: A Reviewcited by 105
  24. 2017Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledgecited by 96
  25. 2023Score-based Data Assimilationcited by 96
  26. 2019Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discoverycited by 93
  27. 2021PySINDy: A comprehensive Python package for robust sparse system identificationcited by 89
  28. 2024Constrained Synthesis with Projected Diffusion Modelscited by 89
  29. 2019DeepMoD: Deep learning for Model Discovery in noisy datacited by 71
  30. 2023ODEFormer: Symbolic Regression of Dynamical Systems with Transformerscited by 62
  31. 2022Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discoverycited by 46
  32. 2021Discovery of Nonlinear Dynamical Systems using a Runge-Kutta Inspired Dictionary-based Sparse Regression Approachcited by 36
  33. 2022A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledgecited by 31
  34. 2021Discovering Sparse Interpretable Dynamics from Partial Observationscited by 25
  35. 2022PDE-LEARN: Using Deep Learning to Discover Partial Differential Equations from Noisy, Limited Datacited by 20
  36. 2021MLReal: Bridging the gap between training on synthetic data and real data applications in machine learningcited by 19
  37. 2022WeakIdent: Weak formulation for Identifying Differential Equations using Narrow-fit and Trimmingcited by 18
  38. 2023Weak-PDE-LEARN: A Weak Form Based Approach to Discovering PDEs From Noisy, Limited Datacited by 16

50 most cited of 57 All 57 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PHDME: Physics-Informed Diffusion Models without Explicit Governing Equations
  2. 2025Incomplete Data, Complete Dynamics: A Diffusion Approach
  3. 2026PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements
  4. 2026PILD: Physics-Informed Learning via Diffusion
  5. 2025Guiding diffusion models to reconstruct flow fields from sparse data
  6. 2026LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization
  7. 2025Discovering Mathematical Equations with Diffusion Language Model
  8. 2024Stochastic Reconstruction of Gappy Lagrangian Turbulent Signals by Conditional Diffusion Models