Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation

• URL: http://arxiv.org/abs/2606.18509v1
• Date: Tue, 16 Jun 2026 21:53:01 GMT
• Title: Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
• Abstract summary: We introduce concept modulation models (CMMs), an attribute-indexed class of conditional generative models with structure $Ato to Cto X$.<n>We show that CMMs lift identifiability to conditional settings by showing that feature agreement on observed attributes induces a latent concept transition constrained by the CMM class.
• Score: 19.425749551382093
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines latent structure, and how that structure determines distributions at unseen attributes. However, existing identifiability and extrapolation guarantees are largely model-specific, with separate analyses in nonlinear ICA, causal representation learning, perturbation modeling, and related conditional latent variable models. We introduce concept modulation models (CMMs), an attribute-indexed class of conditional generative models with structure $A\to Λ\to C\to X$, where attributes select modulators, modulators induce latent concept laws, and concepts generate observed features. CMMs lift transition-based identifiability to conditional settings by showing that feature agreement on observed attributes induces a latent concept transition constrained by the CMM class. We express these constraints through attribute potentials, log-density ratios between attribute-conditioned concept laws, separating the generic lifting step from model-specific rigidity arguments. The same potentials control extrapolation: agreement at unseen attributes holds exactly when the transported attribute-potential identities extend to those attributes. This yields algebraic extrapolation criteria, identifies the common potential-based proof objects behind several existing identifiability and extrapolation results, and, when combined with the model-specific rigidity arguments in those works, recovers their stated conclusions.

Related papers

• Relational Structural Causal Models [52.818153111470394]
  We develop relational structural causal models, extending structural causal models to settings where objects and their relations vary.<n>We propose relational neural causal models, a provably correct approach that outperforms non-relational baselines on simulated traffic scenes.
  arXiv  Detail & Related papers  (2026-06-12T18:54:06Z)
• Statistical and structural identifiability in representation learning [31.990445585569688]
  We formalize two distinct concepts: statistical identifiability and structural identifiability.<n>We prove a statistical $$-near-identifiability result for the representations of models with nonlinear decoders.<n>With additional assumptions on the data-generating process, statistical identifiability extends to structural identifiability.
  arXiv  Detail & Related papers  (2026-03-12T14:19:58Z)
• Model Correlation Detection via Random Selection Probing [62.093777777813756]
  Existing similarity-based methods require access to model parameters or produce scores without thresholds.<n>We introduce Random Selection Probing (RSP), a hypothesis-testing framework that formulates model correlation detection as a statistical test.<n>RSP produces rigorous p-values that quantify evidence of correlation.
  arXiv  Detail & Related papers  (2025-09-29T01:40:26Z)
• SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging [60.83635006372403]
  textttSE-Merging is a self-enhanced model merging framework.<n>We show that textttSE-Merging achieves dynamic model merging without additional training.
  arXiv  Detail & Related papers  (2025-06-22T18:38:41Z)
• Measuring axiomatic soundness of counterfactual image models [24.749839878737884]
  We present a general framework for evaluating image counterfactuals. We define counterfactuals as functions of an input variable, its parents, and counterfactual parents. We show how these metrics can be used to compare and choose between different approximate counterfactual inference models.
  arXiv  Detail & Related papers  (2023-03-02T13:59:07Z)
• Representation Disentaglement via Regularization by Causal Identification [3.9160947065896803]
  We propose the use of a causal collider structured model to describe the underlying data generative process assumptions in disentangled representation learning. For this, we propose regularization by identification (ReI), a modular regularization engine designed to align the behavior of large scale generative models with the disentanglement constraints imposed by causal identification.
  arXiv  Detail & Related papers  (2023-02-28T23:18:54Z)
• Indeterminacy in Latent Variable Models: Characterization and Strong Identifiability [3.959606869996233]
  We construct a theoretical framework for analyzing the indeterminacies of latent variable models. We then investigate how we might specify strongly identifiable latent variable models.
  arXiv  Detail & Related papers  (2022-06-02T00:01:27Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Translational Concept Embedding for Generalized Compositional Zero-shot Learning [73.60639796305415]
  Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework.
  arXiv  Detail & Related papers  (2021-12-20T21:27:51Z)
• Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept [56.46135010588918]
  We prove that the widely used class of RNN-Transducer models and segmental models (direct HMM) are equivalent. It is shown that blank probabilities translate into segment length probabilities and vice versa.
  arXiv  Detail & Related papers  (2021-04-13T11:20:48Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)
• ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA [11.919315372249802]
  We consider the identifiability theory of probabilistic models. We show that our model can be used for the estimation of the components in the framework of Independently Modulated Component Analysis.
  arXiv  Detail & Related papers  (2020-02-26T14:43:30Z)

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.