Uncertainty Estimation for Molecular Diffusion Models

• URL: http://arxiv.org/abs/2606.13451v1
• Date: Thu, 11 Jun 2026 15:11:12 GMT
• Title: Uncertainty Estimation for Molecular Diffusion Models
• Abstract summary: We propose a method for estimating per-sample uncertainty in pretrained molecular diffusion models.<n>We show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics.
• Score: 19.558889439598254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.

Related papers

• Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation [10.056180810643774]
  We show how uncertainty propagates through diffusion inference and degrades sampling quality.<n>We propose UCD (Uncertainty-Calibrated Diffusion), a simple yet effective method that calibrates the reverse diffusion process to account for uncertainty.
  arXiv  Detail & Related papers  (2026-06-01T02:48:22Z)
• Flow Matching with Uncertainty Quantification and Guidance [14.952056744888912]
  Uncertainty-aware flow matching (UA-Flow) is a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty.<n>UA-Flow estimates per-sample uncertainty by propagating velocity uncertainty through the flow dynamics.<n>Experiments on image generation show that UA-Flow produces uncertainty signals more highly correlated with sample fidelity than baseline methods.
  arXiv  Detail & Related papers  (2026-02-10T22:03:13Z)
• Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection [10.061197311881287]
  We propose a novel framework, Diffusion Epistemic Uncertainty with Asymmetric Learning(DEUA), for detecting generated images.<n>We introduce Diffusion Epistemic Uncertainty(DEU) estimation via the Laplace approximation to assess the proximity of data to the manifold of diffusion-generated samples.
  arXiv  Detail & Related papers  (2026-01-21T03:57:15Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• Generative Uncertainty in Diffusion Models [17.06573336804057]
  We propose a Bayesian framework for estimating generative uncertainty of synthetic samples.<n>We show that the proposed generative uncertainty effectively identifies poor-quality samples and significantly outperforms existing uncertainty-based methods.
  arXiv  Detail & Related papers  (2025-02-28T10:56:39Z)
• Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation [10.269485943949332]
  We propose to estimate the pixel-wise aleatoric uncertainty during the sampling phase of diffusion models.<n>The uncertainty is computed as the variance of the denoising scores with a perturbation scheme specifically designed for diffusion models.<n>We show that our guided approach leads to better sample generation in terms of FID scores.
  arXiv  Detail & Related papers  (2024-11-29T19:02:08Z)
• Provable Statistical Rates for Consistency Diffusion Models [87.28777947976573]
  Despite the state-of-the-art performance, diffusion models are known for their slow sample generation due to the extensive number of steps involved. This paper contributes towards the first statistical theory for consistency models, formulating their training as a distribution discrepancy minimization problem.
  arXiv  Detail & Related papers  (2024-06-23T20:34:18Z)
• Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models [72.07462371883501]
  We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information. PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-05T09:44:47Z)
• DensePure: Understanding Diffusion Models towards Adversarial Robustness [110.84015494617528]
  We analyze the properties of diffusion models and establish the conditions under which they can enhance certified robustness. We propose a new method DensePure, designed to improve the certified robustness of a pretrained model (i.e. a classifier) We show that this robust region is a union of multiple convex sets, and is potentially much larger than the robust regions identified in previous works.
  arXiv  Detail & Related papers  (2022-11-01T08:18:07Z)
• Fake It Till You Make It: Near-Distribution Novelty Detection by Score-Based Generative Models [54.182955830194445]
  existing models either fail or face a dramatic drop under the so-called near-distribution" setting. We propose to exploit a score-based generative model to produce synthetic near-distribution anomalous data. Our method improves the near-distribution novelty detection by 6% and passes the state-of-the-art by 1% to 5% across nine novelty detection benchmarks.
  arXiv  Detail & Related papers  (2022-05-28T02:02:53Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)

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.