Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures

• URL: http://arxiv.org/abs/2606.00557v1
• Date: Sat, 30 May 2026 06:15:44 GMT
• Title: Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
• Abstract summary: We propose the emphnormalized relevance measure (NRM) framework, which attributes relevance to neurons across layers of arbitrary architectures.<n>The NRM framework subsumes existing propagation-based explanation algorithms by explicitly identifying the underlying quantity being computed.<n>We demonstrate the utility of the framework in computer vision applications, where joint relevance analysis across multiple layers reveals key information flows in VGG16 networks.
• Score: 23.932427893302826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also examine its internal inference mechanisms to capture the complete picture. To explain the internal inference mechanisms of such models, it is essential to analyze the importance of latent representations for a given task. In this paper, we propose the \emph{normalized relevance measure} (NRM) framework -- a novel general explanation procedure that attributes relevance to \emph{arbitrary sets of neurons across layers of arbitrary architectures}. In the NRM framework, relevance of selected neurons is explicitly defined as a normalized signed measure, constructed using simple operations -- marginalization and conditioning based on additive and multiplicative laws -- in analogy to the probability measures. The normalization property further guarantees comparability across layers. The NRM framework subsumes existing propagation-based explanation algorithms by explicitly identifying the underlying quantity being computed. We demonstrate the utility of the framework in computer vision applications, where joint relevance analysis across multiple layers reveals key information flows in VGG16 networks. Overall, the NRM framework provides a general, mathematically grounded approach to understanding how modern NNs propagate information, offering a versatile and broadly applicable foundation for explainable artificial intelligence.

Related papers

• Learning with Covariance Matrices: Principal Component Analysis Meets Learning with Graphs [94.85514873380572]
  This feature article provides an overview of the theoretical foundations for coVariance neural networks (VNNs)<n>Existing theoretical contributions on graph neural networks (GNNs) consider abstract graph representations.<n>This tutorial brings into focus various novel theoretical insights via mathematical analyses of VNNs that have broad signal processing implications.
  arXiv  Detail & Related papers  (2026-09-09T17:28:46Z)
• Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning [52.66717986145448]
  Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI)<n>This paper focuses on neural network (NN)-based generalized additive models (GAMs), a class of self-interpretable models.
  arXiv  Detail & Related papers  (2026-09-05T07:29:42Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• Towards agent-based-model informed neural networks [0.5787117733071417]
  We present a framework for designing neural networks consistent with the underlying principles of agent-based models.<n>We validate the framework across three case studies of increasing complexity.
  arXiv  Detail & Related papers  (2025-12-05T14:50:50Z)
• Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs [3.429783703166407]
  Our framework enables a global dissection of model behavior by analyzing how high-level semantic attributes emerge, interact, and propagate through internal model components.<n>A key innovation is our visualization platform that we named BAGEL, which presents these insights in a structured knowledge graph.<n>Our framework is model-agnostic, scalable, and contributes to a deeper understanding of how deep learning models generalize (or fail to) in the presence of dataset biases.
  arXiv  Detail & Related papers  (2025-07-08T09:30:20Z)
• Nonlinear classification of neural manifolds with contextual information [6.292933471495322]
  We introduce a theoretical framework that leverages latent directions in input space, which can be related to contextual information.<n>We derive an exact formula for the context-dependent manifold capacity that depends on manifold geometry and context correlations.<n>Our framework's increased expressivity captures representation reformatting in deep networks at early stages of the layer hierarchy, previously inaccessible to analysis.
  arXiv  Detail & Related papers  (2024-05-10T23:37:31Z)
• Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression [37.69303106863453]
  The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs) In this paper, we introduce a framework for conducting IB analysis of general NNs. We also perform IB analysis on a close-to-real-scale, which reveals new features of the MI dynamics.
  arXiv  Detail & Related papers  (2023-05-13T21:44:32Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• Universal approximation property of invertible neural networks [76.95927093274392]
  Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling, generative modeling, and representation learning.
  arXiv  Detail & Related papers  (2022-04-15T10:45:26Z)
• Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks [4.153804257347222]
  We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100.
  arXiv  Detail & Related papers  (2022-03-07T10:56:13Z)
• Relating Graph Neural Networks to Structural Causal Models [17.276657786213015]
  Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. We present a theoretical analysis that establishes a novel connection between GNN and SCM. We then establish a new model class for GNN-based causal inference that is necessary and sufficient for causal effect identification.
  arXiv  Detail & Related papers  (2021-09-09T11:16:31Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• A Chain Graph Interpretation of Real-World Neural Networks [58.78692706974121]
  We propose an alternative interpretation that identifies NNs as chain graphs (CGs) and feed-forward as an approximate inference procedure. The CG interpretation specifies the nature of each NN component within the rich theoretical framework of probabilistic graphical models. We demonstrate with concrete examples that the CG interpretation can provide novel theoretical support and insights for various NN techniques.
  arXiv  Detail & Related papers  (2020-06-30T14:46:08Z)

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.