Uncertainty of Network Topology with Applications to Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2511.18813v1
• Date: Mon, 24 Nov 2025 06:39:45 GMT
• Title: Uncertainty of Network Topology with Applications to Out-of-Distribution Detection
• Authors: Sing-Yuan Yeh, Chun-Hao Yang,
• Abstract summary: We introduce a new topological summary for Bayesian neural networks, termed the predictive topological uncertainty (pTU)<n>pTU measures the uncertainty in the interaction between the model and the inputs.<n>As an application, pTU is used to solve the out-of-distribution (OOD) detection problem, which is critical to ensure model reliability.
• Score: 3.251449696624754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Persistent homology (PH) is a crucial concept in computational topology, providing a multiscale topological description of a space. It is particularly significant in topological data analysis, which aims to make statistical inference from a topological perspective. In this work, we introduce a new topological summary for Bayesian neural networks, termed the predictive topological uncertainty (pTU). The proposed pTU measures the uncertainty in the interaction between the model and the inputs. It provides insights from the model perspective: if two samples interact with a model in a similar way, then they are considered identically distributed. We also show that the pTU is insensitive to the model architecture. As an application, pTU is used to solve the out-of-distribution (OOD) detection problem, which is critical to ensure model reliability. Failure to detect OOD input can lead to incorrect and unreliable predictions. To address this issue, we propose a significance test for OOD based on the pTU, providing a statistical framework for this issue. The effectiveness of the framework is validated through various experiments, in terms of its statistical power, sensitivity, and robustness.

Related papers

• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• Bayesian Physics Informed Neural Networks for Reliable Transformer Prognostics [1.53934570513443]
  This work introduces a Bayesian Physics-Informed Neural Network (B-PINN) framework for probabilistic prognostics estimation.<n>The framework is validated against a finite element model developed and tested with real measurements from a solar power plant.<n>Results, benchmarked against a dropout-PINN baseline, show that the proposed B-PINN delivers more reliable prognostic predictions by accurately quantifying predictive uncertainty.
  arXiv  Detail & Related papers  (2025-09-19T12:39:15Z)
• UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles [42.37986459997699]
  We propose an approach for decomposing uncertainty in SHAP values into aleatoric, epistemic, and entanglement components.<n>We validate the method across three real-world use cases with descriptive statistical analyses.<n>This understanding can guide the development of robust decision-making processes and the refinement of models in high-stakes applications.
  arXiv  Detail & Related papers  (2025-08-13T09:20:33Z)
• TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation [11.334867025651233]
  We propose TULiP, a theoretically-driven uncertainty estimator for OOD detection.<n>Our approach considers a hypothetical perturbation applied to the network before convergence.<n>Our method exhibits state-of-the-art performance, particularly for near-distribution samples.
  arXiv  Detail & Related papers  (2025-05-22T17:16:41Z)
• Testing and Improving the Robustness of Amortized Bayesian Inference for Cognitive Models [0.5223954072121659]
  Contaminant observations and outliers often cause problems when estimating the parameters of cognitive models.<n>In this study, we test and improve the robustness of parameter estimation using amortized Bayesian inference.<n>The proposed method is straightforward and practical to implement and has a broad applicability in fields where outlier detection or removal is challenging.
  arXiv  Detail & Related papers  (2024-12-29T21:22:24Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Leveraging a Probabilistic PCA Model to Understand the Multivariate Statistical Network Monitoring Framework for Network Security Anomaly Detection [64.1680666036655]
  We revisit anomaly detection techniques based on PCA from a probabilistic generative model point of view. We have evaluated the mathematical model using two different datasets.
  arXiv  Detail & Related papers  (2023-02-02T13:41:18Z)
• Pitfalls of Climate Network Construction: A Statistical Perspective [13.623860700196625]
  We simulate time-dependent isotropic random fields on the sphere and apply common network construction techniques. We find several ways in which the uncertainty stemming from the estimation procedure has major impact on network characteristics.
  arXiv  Detail & Related papers  (2022-11-05T11:59:55Z)
• Neural Causal Models for Counterfactual Identification and Estimation [62.30444687707919]
  We study the evaluation of counterfactual statements through neural models. First, we show that neural causal models (NCMs) are expressive enough. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions.
  arXiv  Detail & Related papers  (2022-09-30T18:29:09Z)
• Causal Inference in Geoscience and Remote Sensing from Observational Data [9.800027003240674]
  We try to estimate the correct direction of causation using a finite set of empirical data. We illustrate performance in a collection of 28 geoscience causal inference problems. The criterion achieves state-of-the-art detection rates in all cases, it is generally robust to noise sources and distortions.
  arXiv  Detail & Related papers  (2020-12-07T22:56:55Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)

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.