Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures

• URL: http://arxiv.org/abs/2608.16773v1
• Date: Mon, 17 Aug 2026 16:20:20 GMT
• Title: Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures
• Abstract summary: Abductive Latent Explanations (ALE) were introduced to provide formal, mathematically guaranteed explanations.<n>ALEs rely on computing tight bounds on latent space distances to produce formal explanations.<n>In this work, we generalize the ALE framework to support non-Euclidean prototype architectures.
• Score: 7.001970497421476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to provide formal, mathematically guaranteed explanations that leverage the intrinsic structure of these networks to ensure both predictive safety and human readability. ALEs rely on computing tight bounds on latent space distances to produce formal explanations. However, existing ALE formulations are rigidly confined to Euclidean latent spaces. This leaves a critical gap: modern state-of-the-art architectures increasingly rely on non-Euclidean representations - such as spherical metrics, Gaussian densities, and dimensional projections - rendering current formal explanation methods incompatible. In this work, we generalize the ALE framework to support non-Euclidean prototype architectures. For each geometric variant, we systematically derive how to either map the architecture to existing bounds or construct novel, architecture-specific bounding algorithms. We validate our theoretical constructions by computing subset-minimal formal explanations on fully trained image classifiers. By unifying these diverse models under a single formal framework, we enable the first rigorous, cross-architecture comparison of their interpretability.

Related papers

• An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars [54.11540943172608]
  Deep neural networks are widely believed to derive their expressive power from their ability to form textbfhierarchical representations<n>In language modeling, textbftransformers have emerged as the dominant architecture, with early layers capturing local syntactic patterns and later layers encoding more complex clause-level dependencies.<n>We argue that these architectures possess the structural capacity to encode abstract grammatical states into low-dimensional, linearly separable subspaces within the residual stream.
  arXiv  Detail & Related papers  (2026-06-16T05:02:13Z)
• Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs [0.0]
  We formalize the underlying structural and geometric friction as the textitImpedance Mismatch.<n>We propose a rigorous theoretical roadmap to achieve true semantic fusion.<n>This framework paves the way for models that seamlessly fuse the precision of symbolic logic with the expressivity of parametric memory.
  arXiv  Detail & Related papers  (2026-04-21T17:30:15Z)
• A General Method for Proving Networks Universal Approximation Property [3.565474315629056]
  This paper proposes a general and modular framework for proving universal approximation.<n>We show that any deep network composed of such modules inherently retains the universal approximation property.
  arXiv  Detail & Related papers  (2025-11-11T05:48:34Z)
• Native Logical and Hierarchical Representations with Subspace Embeddings [25.274936769664098]
  We introduce a novel paradigm: embedding concepts as linear subspaces.<n>It naturally supports set-theoretic operations like intersection (conjunction) and linear sum (disjunction)<n>Our method achieves state-of-the-art results in reconstruction and link prediction on WordNet.
  arXiv  Detail & Related papers  (2025-08-21T18:29:17Z)
• TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations [0.9179857807576733]
  Recent work has provided compelling evidence challenging the foundational manifold hypothesis for the token embedding spaces of Large Language Models.<n>We formalize this problem in the language of scheme theory and propose a rigorous resolution by applying the scheme-theoretic blow-up at each singular point.<n>We prove a formal theorem guaranteeing the geometric regularization of this new space, showing that the original pathologies are resolved.
  arXiv  Detail & Related papers  (2025-07-26T02:39:54Z)
• Compositional Structures in Neural Embedding and Interaction Decompositions [101.40245125955306]
  We describe a basic correspondence between linear algebraic structures within vector embeddings in artificial neural networks. We introduce a characterization of compositional structures in terms of "interaction decompositions" We establish necessary and sufficient conditions for the presence of such structures within the representations of a model.
  arXiv  Detail & Related papers  (2024-07-12T02:39:50Z)
• Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation [54.50526986788175]
  Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs. We present a unified view of these models, formulating such layers as implicit causal self-attention layers. Our framework compares the underlying mechanisms on similar grounds for different layers and provides a direct means for applying explainability methods.
  arXiv  Detail & Related papers  (2024-05-26T09:57:45Z)
• 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)
• Inter-layer Transition in Neural Architecture Search [89.00449751022771]
  The dependency between the architecture weights of connected edges is explicitly modeled in this paper. Experiments on five benchmarks confirm the value of modeling inter-layer dependency and demonstrate the proposed method outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-30T03:33:52Z)
• Orthologics for Cones [5.994412766684843]
  In this paper we study logics for such geometric structures. We describe an extension of minimal orthologic with a partial modularity rule that holds for closed convex cones. This logic combines a feasible data structure (exploiting convexity/conicity) with sufficient expressivity, including full orthonegation.
  arXiv  Detail & Related papers  (2020-08-07T13:28:27Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)

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.