From Layers to Networks: Comparing Neural Representations via Diffusion Geometry

• URL: http://arxiv.org/abs/2605.15901v1
• Date: Fri, 15 May 2026 12:40:23 GMT
• Title: From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
• Abstract summary: We use diffusion geometry for neural representations, incorporating tools from multi-view learning into this field for the first time.<n>We perform extensive numerical experiments, evaluating our measures on the Representational Similarity (ReSi) benchmark.<n>Our methods achieve SoTA results in accuracy and output correlation for both language and vision tasks across different models.
• Score: 3.6731536660959985
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion geometry is a manifold learning framework that uses random walks defined by Markov transition matrices to characterize the geometry of a dataset at multiple scales. We use diffusion geometry for neural representations, incorporating tools from multi-view learning into this field for the first time. Our key technical observation is that a broad class of similarity measures based on representational similarity matrices (RSMs) admits a closed-form equivalent formulation in terms of row-stochastic Markov matrices, opening the door to manipulations from diffusion geometry. As a first application, we develop multi-scale variants of Centered Kernel Alignment and Distance Correlation, which utilise the $t^{th}$ power of the underlying transition matrix to probe the data geometry at adjustable diffusion scales. Going further, we introduce variants of these measures which fuse the Markov matrices of several layers via alternating diffusion into a single operator that captures the network's joint sample geometry, allowing similarity to be computed across multiple layers and shifting the comparison from layer-to-layer to network-to-network. We perform extensive numerical experiments, evaluating our measures on the Representational Similarity (ReSi) benchmark comprising 14 architectures trained on 7 datasets across three different domains. Our methods achieve SoTA results in accuracy and output correlation for both language and vision tasks across different models. We furthermore show SoTA performance on an additional benchmark evaluating on out-of-distribution data.

Related papers

• Riemannian Networks over Full-Rank Correlation Matrices [102.84784139051526]
  Full-rank correlation matrices are a normalized alternative to the Symmetric Positive Definite (SPD) manifold.<n>We extend basic layers, including Multinomial Logistic Regression (MLR), Fully Connected (FC) and convolutional layers, to these geometries.<n>We also present methods for accurate backpropagation for two correlation geometries.
  arXiv  Detail & Related papers  (2026-05-18T19:54:55Z)
• Tabular data generation with tensor contraction layers and transformers [0.35998666903987897]
  We investigate the potential of using embedding representations on data generation, utilizing tensor contraction layers and transformers.<n>Our empirical study, conducted across multiple datasets from the OpenML CC18 suite, compares models over density estimation and Machine Learning efficiency metrics.<n>The main takeaway from our results is that leveraging embedding representations with the help of tensor contraction layers improves density estimation metrics, albeit maintaining competitive performance in terms of machine learning efficiency.
  arXiv  Detail & Related papers  (2024-12-06T19:34:13Z)
• Symmetry Discovery for Different Data Types [52.2614860099811]
  Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. We propose LieSD, a method for discovering symmetries via trained neural networks which approximate the input-output mappings of the tasks. We validate the performance of LieSD on tasks with symmetries such as the two-body problem, the moment of inertia matrix prediction, and top quark tagging.
  arXiv  Detail & Related papers  (2024-10-13T13:39:39Z)
• The geometry of hidden representations of large transformer models [43.16765170255552]
  Large transformers are powerful architectures used for self-supervised data analysis across various data types. We show that the semantic structure of the dataset emerges from a sequence of transformations between one representation and the next. We show that the semantic information of the dataset is better expressed at the end of the first peak, and this phenomenon can be observed across many models trained on diverse datasets.
  arXiv  Detail & Related papers  (2023-02-01T07:50:26Z)
• Geometric Scattering on Measure Spaces [15.819230791757906]
  We introduce a general, unified model for geometric scattering on measure spaces.<n>We consider finite measure spaces that are obtained from randomly sampling an unknown manifold.<n>We propose two methods for constructing a data-driven graph on which the associated graph scattering transform approximates the scattering transform on the underlying manifold.
  arXiv  Detail & Related papers  (2022-08-17T22:40:09Z)
• Manifold Topology Divergence: a Framework for Comparing Data Manifolds [109.0784952256104]
  We develop a framework for comparing data manifold, aimed at the evaluation of deep generative models. Based on the Cross-Barcode, we introduce the Manifold Topology Divergence score (MTop-Divergence) We demonstrate that the MTop-Divergence accurately detects various degrees of mode-dropping, intra-mode collapse, mode invention, and image disturbance.
  arXiv  Detail & Related papers  (2021-06-08T00:30:43Z)
• TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation [141.2690520327948]
  We propose a two-stream graph convolutional network (TSGCNet) to learn multi-view information from different geometric attributes. We evaluate our proposed TSGCNet on a real-patient dataset of dental models acquired by 3D intraoral scanners.
  arXiv  Detail & Related papers  (2020-12-26T08:02:56Z)
• Primal-Dual Mesh Convolutional Neural Networks [62.165239866312334]
  We propose a primal-dual framework drawn from the graph-neural-network literature to triangle meshes. Our method takes features for both edges and faces of a 3D mesh as input and dynamically aggregates them. We provide theoretical insights of our approach using tools from the mesh-simplification literature.
  arXiv  Detail & Related papers  (2020-10-23T14:49:02Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)
• Learning Flat Latent Manifolds with VAEs [16.725880610265378]
  We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points. We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one. We evaluate our method on a range of data-sets, including a video-tracking benchmark.
  arXiv  Detail & Related papers  (2020-02-12T09:54:52Z)

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.