From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

• URL: http://arxiv.org/abs/2606.11831v1
• Date: Wed, 10 Jun 2026 09:14:45 GMT
• Title: From Uniform to Learned Graph Priors: Diffusion for Structure Discovery
• Abstract summary: We propose Diff-prior, a diffusion-parameterized adaptive prior used to calibrate latent graph distribution rather than generate graphs.<n>Our core insight is to reframe prior integration as a learnable denoising-style calibration that organizes scattered, uncertain edge posteriors into a more reliable structure.<n>Experiments on standard benchmarks validated our framework, and the results indicate that Diff-prior improves the performance of structure inference.
• Score: 18.139196723025034
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. However, these methods typically rely on oversimplified, factorized graph priors. Such priors, typically nearing uniform distributions, treat edges as independent entities. This systemic misalignment does not match the real-world systems and yields diffuse and indecisive edge posteriors limiting the reliability of structural discovery. To address this, we propose \textit{Diff-prior}, a diffusion-parameterized adaptive prior used to calibrate latent graph distribution rather than generate graphs. Our core insight is to reframe prior integration as a learnable denoising-style calibration that organizes scattered, uncertain edge posteriors into a more reliable overall structure which can be trained by the diffusion model. Diff-prior learns an adaptive structure prior that performs structured calibration on the edge posteriors during inference, guiding it towards a distribution closer to the underlying structure. The diff-prior operates before structural sampling and acts as a denoising calibrator directly on the encoder edge distribution, which provides a generic training paradigm over structured variables. Experiments on standard benchmarks validated our framework, and the results indicate that Diff-prior improves the performance of structure inference and generates more decisive edge posteriors across multiple NRI-family architectures. The code is available on https://github.com/Hardy158118/Diffprior.

Related papers

• Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction [22.26159235291006]
  We present Learning Gaussian Structure (LGS), a framework that enhances both Gaussian structure and primitive attributes.<n>Our key observation is that changes in local responses induced by a prune or add intervention reveal whether the structural adjustment benefits reconstruction.<n>We develop a compact Cross-Time Point Query that explicitly retrieves and aggregates neighboring features from Gaussian primitives at other timestamps for reliable attribute prediction.
  arXiv  Detail & Related papers  (2026-08-11T15:38:55Z)
• DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining [8.304025820176394]
  We introduce DIFF-ERO, a conformance-aware loss function for deep learning models on process data.<n>DIFF-ERO is a differentiable formulation of entropy-based conformance that incorporates control-flow information during training.<n>We show improved predictive performance where structure matters most while maintaining parity elsewhere.
  arXiv  Detail & Related papers  (2026-06-12T09:06:05Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Prior-Informed Flow Matching for Graph Reconstruction [38.96153306484745]
  We introduce Prior-Informed Flow Matching (PIFM), a conditional flow model for graph reconstruction.<n>PIFM bridges the gap by integrating embedding-based priors with continuous-time flow matching.<n> Experiments on different datasets demonstrate that PIFM consistently enhances classical embeddings, outperforming them and state-of-the-art generative baselines in reconstruction accuracy.
  arXiv  Detail & Related papers  (2026-01-29T18:38:02Z)
• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss [53.542743390809356]
  This paper aims to provide a first-principles analysis of the Expectation of Optimization Bias (EOB)<n>Our analysis reveals a fundamental paradigm paradox: the more deterministic and structured the time series, the more severe the bias by point-wise loss function.<n>We present a concrete solution that simultaneously achieves both principles via DFT or DWT.
  arXiv  Detail & Related papers  (2025-12-21T06:08:22Z)
• DAG DECORation: Continuous Optimization for Structure Learning under Hidden Confounding [0.0]
  We study structure learning for linear Gaussian SEMs in the presence of latent confounding.<n>We propose textscDECOR, a single likelihood-based estimator that jointly learns a DAG and a correlated noise model.
  arXiv  Detail & Related papers  (2025-10-02T15:23:30Z)
• Graph Transformer Networks for Accurate Band Structure Prediction: An End-to-End Approach [37.28844299368596]
  We introduce a graph Transformer-based end-to-end approach that directly predicts band structures from crystal structures with high accuracy.<n>We demonstrate that our model not only provides accurate band structure predictions but also can derive other properties (such as band gap, band center, and band dispersion) with high accuracy.
  arXiv  Detail & Related papers  (2024-11-25T15:22:03Z)
• Graph Structure Learning with Interpretable Bayesian Neural Networks [10.957528713294874]
  We introduce novel iterations with independently interpretable parameters. These parameters influence characteristics of the estimated graph, such as edge sparsity. After unrolling these iterations, prior knowledge over such graph characteristics shape prior distributions. Fast execution and parameter efficiency allow for high-fidelity posterior approximation.
  arXiv  Detail & Related papers  (2024-06-20T23:27:41Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)
• Local Graph-homomorphic Processing for Privatized Distributed Systems [57.14673504239551]
  We show that the added noise does not affect the performance of the learned model. This is a significant improvement to previous works on differential privacy for distributed algorithms.
  arXiv  Detail & Related papers  (2022-10-26T10:00:14Z)
• DiBS: Differentiable Bayesian Structure Learning [38.01659425023988]
  We propose a general, fully differentiable framework for Bayesian structure learning (DiBS) DiBS operates in the continuous space of a latent probabilistic graph representation. Contrary to existing work, DiBS is agnostic to the form of the local conditional distributions.
  arXiv  Detail & Related papers  (2021-05-25T11:23:08Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)

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.