Learning Coherent Representations: A Topological Approach to Interpretability

• URL: http://arxiv.org/abs/2606.02841v1
• Date: Mon, 01 Jun 2026 20:05:58 GMT
• Title: Learning Coherent Representations: A Topological Approach to Interpretability
• Abstract summary: Deep neural networks learn representations where individual features often lack interpretable meaning.<n>We introduce coherence, a geometric property inspired by neural coding in the brain, where neurons like grid cells respond to contiguous regions of state space.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks learn representations where individual features often lack interpretable meaning; a single neuron may activate for scattered, unrelated inputs. We introduce coherence, a geometric property inspired by neural coding in the brain, where neurons like grid cells and head direction cells respond to contiguous regions of state space. A non-negative matrix is coherent if each row (sample) attends to geometrically clustered columns (features) and vice versa, and in addition every sample is well described by some feature and every feature is needed by some sample. We prove that coherent matrices induce a bounded interleaving between the Vietoris-Rips filtrations of samples and features, guaranteeing that both spaces share compatible topological structure. This geometric constraint facilitates interpretability. For example, if data lies on a circle, coherent features must tile that circle into contiguous arcs. We introduce Coh, a differentiable objective function based on Fréchet variance that enforces coherence during training. Unlike sparsity, which bounds how many samples a feature activates on, coherence bounds which samples, requiring geometric connectivity rather than only rarity. This yields not just interpretable features but an interpretable feature space. We validate Coh in an auto-encoder using synthetic and rotated MNIST datasets and in a token embedding of BERT using language data.

Related papers

• Critical Percolation as a Synthetic Data Model for Interpretability [0.0]
  We introduce a family of synthetic datasets consisting of hierarchical functions defined on critical mean-field percolation clusters.<n>Latent variables modeling a taxonomic hierarchy generate each data point's target value.<n>We find that the model's ground-truth latent variables can be linearly decoded from neural network activations.
  arXiv  Detail & Related papers  (2026-06-18T15:15:57Z)
• Neural Point-Forms [1.0262304700896199]
  We introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs)<n>NPFs provide a competitive, and interpretable representation, with the strongest benefits appearing when labels depend on sampling density, manifold-like structure, or response-relevant population geometry.
  arXiv  Detail & Related papers  (2026-05-15T01:44:31Z)
• Convergent Evolution: How Different Language Models Learn Similar Number Representations [53.8769088563044]
  Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$.<n>Transformers, Linear RNNs, LSTMs, and classical word embeddings all learn features that have period-$T$ spikes in the Fourier domain.<n>Only some learn geometrically separable features that can be used to linearly classify a number mod-$T$.
  arXiv  Detail & Related papers  (2026-04-22T17:45:27Z)
• How high is `high'? Rethinking the roles of dimensionality in topological data analysis and manifold learning [8.397730500554047]
  We present a generalised Hanson-Wright inequality and use it to establish new statistical insights into the geometry of data point-clouds.<n>We revisit the ground-breaking neuroscience discovery of isometric toroidal structure in grid-cell activity made by Gardner et al.<n>Our findings reveal, for the first time, evidence that this structure is in fact to physical space, meaning that grid cell activity conveys a geometrically faithful representation of the real world.
  arXiv  Detail & Related papers  (2025-05-22T16:34:15Z)
• Making Sense Of Distributed Representations With Activation Spectroscopy [44.94093096989921]
  There is growing evidence to suggest that relevant features are encoded across many neurons in a distributed fashion.<n>This work explores one feasible path to both detecting and tracing the joint influence of neurons in a distributed representation.
  arXiv  Detail & Related papers  (2025-01-26T07:33:42Z)
• Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory [64.06519549649495]
  We provide the definition of what we call functionally equivalent features. These features produce equivalent output under certain transformations. We propose an efficient algorithm named Iterative Feature Merging.
  arXiv  Detail & Related papers  (2023-10-10T16:27:12Z)
• Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles [34.32021888691789]
  We develop a theory of feature-bagging in noisy least-squares ridge ensembles. We demonstrate that subsampling shifts the double-descent peak of a linear predictor. We compare the performance of a feature-subsampling ensemble to a single linear predictor.
  arXiv  Detail & Related papers  (2023-07-06T17:56:06Z)
• A Self-Encoder for Learning Nearest Neighbors [5.297261090056809]
  The self-encoder learns to distribute the data samples in the embedding space so that they are linearly separable from one another. Unlike regular nearest neighbors, the predictions resulting from this encoding of data are invariant to any scaling of features.
  arXiv  Detail & Related papers  (2023-06-25T14:30:31Z)
• Dist2Cycle: A Simplicial Neural Network for Homology Localization [66.15805004725809]
  Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations. We propose a graph convolutional model for learning functions parametrized by the $k$-homological features of simplicial complexes.
  arXiv  Detail & Related papers  (2021-10-28T14:59:41Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)
• Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning [175.34232468746245]
  We introduce a parameterization method called Neural Bayes. It allows computing statistical quantities that are in general difficult to compute. We show two independent use cases for this parameterization.
  arXiv  Detail & Related papers  (2020-02-20T22:28:53Z)

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.