A homotopy-type-theoretic generalization of neurosymbolic inference

• URL: http://arxiv.org/abs/2606.17851v1
• Date: Tue, 16 Jun 2026 12:22:12 GMT
• Title: A homotopy-type-theoretic generalization of neurosymbolic inference
• Abstract summary: neurosymbolic (NeSy) systems compute one functional: a belief-weighted sum of a logical quantity over a space of $$-structures.<n>We develop the framework from scratch for NeSy systems, prove a conservativity theorem that recovers the classical functional when symmetries are trivial, and show that the symmetry our framework exposes is exactly the one behind reasoning shortcuts.
• Score: 46.36639624013224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A wide range of neurosymbolic (NeSy) systems compute one functional: a belief-weighted sum of a logical quantity over a space of $σ$-structures, of which weighted model counting, fuzzy logic, and probabilistic logic are special cases. This account is built on sets, and a set deliberately forgets two things that are important for NeSy: when two $σ$-structures are the same up to a symmetry of the theory, and how many distinct proofs witness a query. Replacing the underlying sets by types, in the sense of homotopy type theory, preserves this information, and turns this functional into a belief-weighted homotopy cardinality, a notion of size that counts each object in inverse proportion to its symmetries. We develop the framework from scratch for NeSy systems, prove a conservativity theorem that recovers the classical functional when symmetries are trivial, and show that the symmetry our framework exposes is exactly the one behind reasoning shortcuts. The payoff is concrete: the shortcut-aware concept posterior that recent methods reach by ensembling or expressive density estimation is the only symmetry-invariant point of the confusion-set simplex, computable in closed form by averaging a single model over the symmetry group. On MNIST reasoning-shortcut benchmarks this single-model wrapper is better calibrated than a diversity-trained ensemble, while leaving label accuracy and identifiable concepts untouched. Code is freely available at https://github.com/bio-ontology-research-group/hott-nesy.

Related papers

• Blind Symmetry Matching in Quantum States with Application to Shot-Count Reduction [1.3537117504260623]
  A basis adapted to a symmetry it carries reduces the repeated measurements needed to read a statistical answer.<n>Two conditions are treated, both detected by the same score with a different projection.<n>Blind symmetry matching is a practical primitive for the common case where the matched basis cannot be written down in advance.
  arXiv  Detail & Related papers  (2026-06-17T15:36:12Z)
• Bootstrapping Symmetries in Quantum Many-Body Systems from the Cross Spectral Form Factor [6.8996092922585675]
  We introduce a bootstrap framework to reconstruct the representation theory of hidden finite group symmetries of quantum many-body lattice Hamiltonians.<n>Our framework applies equally well to chaotic and integrable many-body systems.
  arXiv  Detail & Related papers  (2026-04-01T18:02:36Z)
• Profusion of Symmetry-Protected Qubits from Stable Ergodicity Breaking [0.0]
  We show how combining a discrete symmetry with topological space fragmentation can give rise to exponentially many topologically stable qubits protected by a single discrete symmetry.<n>We also comment on the combination of symmetry enrichment and topological fragmentation more generally, and the implications for use of systems exhibiting Hilbert space fragmentation as quantum memories.
  arXiv  Detail & Related papers  (2025-12-23T14:30:06Z)
• A Canonicalization Perspective on Invariant and Equivariant Learning [54.44572887716977]
  We introduce a canonicalization perspective that provides an essential and complete view of the design of frames. We show that there exists an inherent connection between frames and canonical forms. We design novel frames for eigenvectors that are strictly superior to existing methods.
  arXiv  Detail & Related papers  (2024-05-28T17:22:15Z)
• Global optimality under amenable symmetry constraints [0.5656581242851759]
  We show the interplay between convexity, the group, and the underlying vector space, which is typically infinite-dimensional. We apply this toolkit to the invariant optimality problem. It yields new results on invariant kernel mean embeddings and risk-optimal invariant couplings.
  arXiv  Detail & Related papers  (2024-02-12T12:38:20Z)
• Equivariant Symmetry Breaking Sets [0.6475999521931204]
  Equivariant neural networks (ENNs) have been shown to be extremely effective in applications involving underlying symmetries. We propose a novel symmetry breaking framework that is fully equivariant and is the first which fully addresses spontaneous symmetry breaking.
  arXiv  Detail & Related papers  (2024-02-05T02:35:11Z)
• A Study of Neural Collapse Phenomenon: Grassmannian Frame, Symmetry and Generalization [91.95109845914267]
  We extend original Neural Collapse Phenomenon by proving Generalized Neural Collapse hypothesis. We obtain Grassmannian Frame structure from the optimization and generalization of classification. We provide a theorem to explain Symmetric Generalization of permutation.
  arXiv  Detail & Related papers  (2023-04-18T11:35:14Z)
• Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance [72.50214227616728]
  Interpretability methods are valuable only if their explanations faithfully describe the explained model. We consider neural networks whose predictions are invariant under a specific symmetry group.
  arXiv  Detail & Related papers  (2023-04-13T17:59:03Z)
• Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles [55.41644538483948]
  We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the transformations symmetry and the corresponding generators. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.
  arXiv  Detail & Related papers  (2023-01-13T16:25:25Z)
• Quantum Mechanics as a Theory of Incompatible Symmetries [77.34726150561087]
  We show how classical probability theory can be extended to include any system with incompatible variables. We show that any probabilistic system (classical or quantal) that possesses incompatible variables will show not only uncertainty, but also interference in its probability patterns.
  arXiv  Detail & Related papers  (2022-05-31T16:04:59Z)
• Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron [21.356438315715888]
  We consider the symmetric binary perceptron model, a simple model of neural networks. We establish several conjectures for this model. Our proof technique relies on a dense counter-part of the small graph conditioning method.
  arXiv  Detail & Related papers  (2021-02-25T18:39:08Z)

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.