Neural Feature Governance: Extending Atom Prevalence

• URL: http://arxiv.org/abs/2607.21671v1
• Date: Thu, 23 Jul 2026 08:50:12 GMT
• Title: Neural Feature Governance: Extending Atom Prevalence
• Abstract summary: This paper introduces Neural Atom Prevalence (NAP), a principled Bayesian framework for structured node-level model selection in feedforward neural networks.<n>Nap achieves state-of-the-art structural sparsity, reducing active nodes to as few as 8% of the original dense architecture on MNIST.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Neural network compression and interpretability remain open challenges in modern deep learn- ing, where billion-parameter architectures deliver impressive accuracy at the cost of trans- parency, computational efficiency, and reliable uncertainty quantification. This paper introduces Neural Atom Prevalence (NAP), a principled Bayesian framework for structured node-level model selection in feedforward neural networks. NAP introduces the neural atom (activation unit) and functions as a hybrid method operating through a four-phase pipeline: Bayesian Lottery Ticket (BLT) identification via Iterative Magnitude Pruning (IMP), soft variational training of the Spike and Slab Independent Gaussian (SS-IG) model, Poisson-Binomial (PB) optimal layer-size selection, and Bayesian fine-tuning to produce a sparse, stable, interpretable, and accurate model. Extensive empirical validation across simulated nonlinear regression, two UCI benchmark datasets (Concrete, YearPredictionMSD), and the MNIST image classification task demonstrates that NAP achieves state-of-the-art structural sparsity, reducing active nodes to as few as 8% of the original dense architecture on MNIST, while well-calibrated probabilisti- cally: the aleatoric-epistemic uncertainty decomposition reveals that model ignorance accounts for only 3 to 4% of total predictive variance across all experiments, and regression reliability diagrams confirm a near-nominal predictive interval coverage (93.4% observed against a 95% target). These results establish NAP as a reliable, theoretically grounded, and computation- ally tractable solution to the simultaneous pursuit of sparsity, accuracy, interpretability, and uncertainty quantification in Bayesian neural networks.

Related papers

• Bayesian Interpolating Neural Network (B-INN): a scalable and reliable Bayesian model for large-scale physical systems [0.8593015118377854]
  This paper proposes a scalable and reliable Bayesian surrogate model, termed the Bayesian Interpolating Neural Network (B-INN)<n>B-INN combines high-order theory with tensor decomposition and alternating direction algorithm to enable effective dimensionality reduction without compromising predictive accuracy.<n> Numerical experiments demonstrate that B-INNs can be from 20 times to 10,000 times faster with a robust uncertainty estimation.
  arXiv  Detail & Related papers  (2026-01-30T11:38:42Z)
• Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach [55.43914153271912]
  Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features.<n>Existing GNNs fail to account for the uncertainty of class probabilities that vary with the depth of the model, leading to unreliable and risky predictions in real-world scenarios.<n>We propose a novel Evidence Fusing Graph Neural Network (EFGNN for short) to achieve trustworthy prediction, enhance node classification accuracy, and make explicit the risk of wrong predictions.
  arXiv  Detail & Related papers  (2025-06-16T03:59:38Z)
• Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer [55.66973223528494]
  We develop a Bayesian Non-negative Decision Layer (BNDL), which reformulates deep neural networks as a conditional Bayesian non-negative factor analysis.<n>BNDL can model complex dependencies and provide robust uncertainty estimation.<n>We also offer theoretical guarantees that BNDL can achieve effective disentangled learning.
  arXiv  Detail & Related papers  (2025-05-28T10:23:34Z)
• Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks [11.815986153374967]
  This article advances LBBNNs by enabling covariates to skip to any succeeding layer or be excluded.<n>The input-skip LBBNN approach reduces network density significantly compared to standard LBBNNs, achieving over 99% reduction for small networks and over 99.9% for larger ones.<n>For example, on MNIST, we reached 97% accuracy and great calibration with just 935 weights, reaching state-of-the-art for compression of neural networks.
  arXiv  Detail & Related papers  (2025-03-13T15:59:03Z)
• Uncertainty Quantification for Multi-fidelity Simulations [0.0]
  The work focuses on gathering high-fidelity and low-fidelity numerical simulations data using Nektar++ and XFOIL respectively.<n>The utilization of the higher distribution in calculating the Coefficient of lift and drag has demonstrated superior accuracy and precision.<n>To minimize the reliability on high-fidelity numerical simulations in Uncertainty Quantification, a multi-fidelity strategy has been adopted.
  arXiv  Detail & Related papers  (2025-03-11T13:11:18Z)
• Neural Conditional Probability for Uncertainty Quantification [22.951644463554352]
  We introduce Neural Conditional Probability (NCP), an operator-theoretic approach to learning conditional distributions.<n>By leveraging the approximation capabilities of neural networks, NCP efficiently handles a wide variety of com- plex probability distributions.<n>In experiments, we show that NCP with a 2-hidden-layer network matches or outperforms leading methods.
  arXiv  Detail & Related papers  (2024-07-01T10:44:29Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)
• Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks [4.376565880192482]
  Deep neural network (DNN) models have achieved state-of-the-art predictive accuracy in a wide range of supervised learning applications. accurately quantifying the uncertainty in DNN predictions remains a challenging task. We propose the Bayesian Deep Noise Neural Network (B-DeepNoise), which generalizes standard Bayesian DNNs by extending the random noise variable to all hidden layers. We evaluate B-DeepNoise against existing methods on benchmark regression datasets, demonstrating its superior performance in terms of prediction accuracy, uncertainty quantification accuracy, and uncertainty quantification efficiency.
  arXiv  Detail & Related papers  (2022-06-12T02:47:29Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.