Beyond Activation Alignment: The Geometry of Neural Sensitivity

• URL: http://arxiv.org/abs/2605.03222v2
• Date: Thu, 07 May 2026 08:48:41 GMT
• Title: Beyond Activation Alignment: The Geometry of Neural Sensitivity
• Abstract summary: We introduce a framework based on local decodable information, which focuses on a representation's ability to discriminate small perturbations.<n>We compare these regularized signatures using a log-spectral distance on the manifold of symmetric positive definite (SPD) matrices.<n> Empirically, this framework enables the recovery of corresponding layers across independently trained artificial neural networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Activation-alignment measures such as Representational Similarity Analysis (RSA), Canonical Correlation Analysis (CCA), and Centered Kernel Alignment (CKA) are widely used to compare biological and artificial neural representations. Recent theoretical work interprets many of these methods as assessing agreement between optimal linear readouts over broad families of global tasks. However, agreement at the level of global readouts does not determine how a system uses local stimulus evidence. Specifically, representations may align in activation space yet differ in their sensitivity to small perturbations. To address this challenge, we introduce a complementary framework based on local decodable information, which focuses on a representation's ability, under noise, to discriminate small perturbations within a specified stimulus-coordinate subspace. Building on Fisher information and local representation geometry, we summarize each representation using the expected projected pullback/Fisher metric over that subspace. This formulation induces a second-moment family of local discrimination tasks, for which the resulting operator provides a minimal, complete dataset-level summary of expected discriminability. We compare these regularized signatures using a log-spectral distance on the manifold of symmetric positive definite (SPD) matrices, yielding the Spectral Riemannian Alignment Score (S-RAS) and a uniform multiplicative certificate over the corresponding family of lifted task values. Empirically, this framework enables the recovery of corresponding layers across independently trained artificial neural networks, supports transferable class-conditional probes, reveals controlled dissociations between standard and robust training, and uncovers stimulus-coordinate family effects across mouse visual cortex using the Allen Brain Observatory static gratings dataset.

Related papers

• Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks [48.553902624178995]
  We train an ensemble of networks on regression and classification tasks using training sets by independent realizations of a noise process.<n>We show that the signal-to-noise ratio (SNR) and the training sample size influence the alignment.<n>Across linear and nonlinear networks, regression and classification tasks, and both synthetic and real-world data, we consistently observe that alignment varies monotonically with SNR.
  arXiv  Detail & Related papers  (2026-05-26T12:58:48Z)
• K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles [65.21921642886367]
  K-Models is a novel framework that integrates ordinal constraints and estimates key underlying elements of the random process generating the observed functional profiles.<n>The proposed method is evaluated through simulations and real-world applications.
  arXiv  Detail & Related papers  (2026-05-14T13:35:44Z)
• Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data [73.20753799870282]
  We propose a novel Divide-and-Conquer Holistic Cognition Network (DHCNet)<n>DHCNet implements a divide-and-conquer strategy by decomposing holistic cues into spatially-associated subtle discrepancies.<n>DHCNet achieves remarkable performance on five widely-used Ultra-FGVC datasets.
  arXiv  Detail & Related papers  (2026-04-21T11:17:09Z)
• Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning [52.452902154360565]
  GTSA-PCA is a geometric extension of Principal Component Analysis.<n>It integrates curvature awareness and geodesic consistency within a unified spectral framework.<n>Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
  arXiv  Detail & Related papers  (2026-04-20T20:36:36Z)
• Implicit Neural Representations: A Signal Processing Perspective [54.57279006229212]
  Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations.<n>This article examines the evolution of INRs from a signal processing perspective, emphasizing spectral behavior, sampling theory, and multiscale representation.<n>We highlight the utility of INRs across a broad range of applications, including inverse problems in medical and radar imaging, compression, and 3D scene representation.
  arXiv  Detail & Related papers  (2026-04-16T14:12:06Z)
• Representation Geometry as a Diagnostic for Out-of-Distribution Robustness [0.5978543974412219]
  We propose a geometry-based diagnostic framework that constructs class-conditional mutual k-nearest-neighbor graphs from in-distribution embeddings.<n>We find that lower spectral complexity and higher mean curvature consistently predict stronger out-of-distribution (OOD) accuracy across checkpoints.<n>Our results demonstrate that representation geometry enables interpretable, label-free diagnosis and supports reliable unsupervised checkpoint selection.
  arXiv  Detail & Related papers  (2026-02-03T19:13:36Z)
• Interpretability of the Intent Detection Problem: A New Approach [0.0]
  Internal mechanisms enabling Recurrent Neural Networks to solve intent detection tasks are poorly understood.<n>We apply dynamical systems theory to analyze how RNN architectures address this problem.<n>Our framework decouples geometric separation from readout alignment, providing a novel, mechanistic explanation for real world performance disparities.
  arXiv  Detail & Related papers  (2026-01-23T20:27:47Z)
• Functional embeddings enable Aggregation of multi-area SEEG recordings over subjects and sessions [0.11083289076967894]
  We propose a representation-learning framework that learns a subject-agnostic functional identity for each electrode from multi-region local field potentials.<n>We evaluate this framework on a 20-subject dataset spanning basal ganglia-thalamic regions collected during flexible rest/movement recording sessions.
  arXiv  Detail & Related papers  (2025-10-31T01:23:05Z)
• VIKING: Deep variational inference with stochastic projections [48.946143517489496]
  Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks.<n>We propose a simple variational family that considers two independent linear subspaces of the parameter space.<n>This allows us to build a fully-correlated approximate posterior reflecting the overparametrization.
  arXiv  Detail & Related papers  (2025-10-27T15:38:35Z)
• BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural Dynamics [0.11744028458220425]
  We introduce Behavior-Adaptive Connectivity Estimation (BACE), an end-to-end framework that learns phase-specific, directed inter-regional connectivity.<n>BACE aggregates many micro-contacts within each anatomical region via per-region temporal encoders.<n>It applies a learnable adjacency specific to each behavioral phase, and is trained on a forecasting objective.
  arXiv  Detail & Related papers  (2025-10-11T22:48:36Z)
• What Representational Similarity Measures Imply about Decodable Information [6.5879381737929945]
  We show that some neural network similarity measures can be equivalently motivated from a decoding perspective. Measures like CKA and CCA quantify the average alignment between optimal linear readouts across a distribution of decoding tasks. Overall, our work demonstrates a tight link between the geometry of neural representations and the ability to linearly decode information.
  arXiv  Detail & Related papers  (2024-11-12T21:37:10Z)
• Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [54.23513799338309]
  We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition. Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-21T02:33:07Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

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.