The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning

• URL: http://arxiv.org/abs/2608.16245v1
• Date: Mon, 17 Aug 2026 08:20:40 GMT
• Title: The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning
• Abstract summary: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate.<n>We introduce a unified, supervised framework that couples latent dimension-covariate dependence with constraints on the latent structure.<n>We show that both post-hoc alignment and iFA enable controllability of structured latent representations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate. Unsupervised approaches typically target latent dimension independence, yet this gives no guarantee that the resulting dimensions align with semantically meaningful covariates. Supervised approaches structure the latent space using observed covariates, but under correlated covariates they cannot simultaneously control one-to-one latent-covariate alignment and latent independence. We introduce a unified, supervised framework that couples latent dimension-covariate dependence with constraints on the latent structure. Within this framework, we show an inherent trade-off, where enforcing latent independence or exclusive one-to-one latent-covariate dependence comes at a provable cost in latent-covariate alignment. We prove that the resulting disentanglement regimes are ordered by the strength of that alignment. Each regime admits a closed-form transformation of the latent space. We apply these transformations post-hoc to realign the representations of pretrained models such as CLIP, DINOv2, and ViT, and we fold them into the inference of informed factor analysis (iFA), a probabilistic model with covariate-informed factors. On simulated and real multi-omics data, we show that both post-hoc alignment and iFA enable controllability of structured latent representations.

Related papers

• DivRL: Disentangled Self-Similarity Rewards for Diverse Subject-Driven Generation [52.23323703015865]
  We propose a post-training framework called DivRL that jointly optimize identity consistency and structural diversity simultaneously.<n>We introduce a Negative Self-Similarity Measure (nSSM) to quantify structural diversity, and Visual Semantic Matching (VSM) to evaluate identity consistency.
  arXiv  Detail & Related papers  (2026-06-22T21:22:42Z)
• Structured Nonparametric Variational Inference for Dependent Latent Modeling [11.146941243243248]
  Variational inference (VI) is a core engine of modern AI, enabling scalable learning and uncertainty-aware training of large probabilistic and generative models.<n>We propose Structured Non Variational Inference (SN-VI), a novel framework for modeling complex dependencies among latent variables in posterior approximation.<n> SN-VI preserves intricate latent variable dependencies, providing a flexible and accurate approximation of posterior boundeds with arbitrary shapes.
  arXiv  Detail & Related papers  (2026-06-13T20:29:04Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Dependence Fidelity and Downstream Inference Stability in Generative Models [0.0]
  Covariance-level dependence fidelity is a useful criterion for evaluating generative models.<n> dependence divergence induces quantitative instability in downstream inference.<n>These results highlight dependence fidelity as a useful diagnostic for evaluating generative models.
  arXiv  Detail & Related papers  (2026-03-17T18:24:31Z)
• Mechanistic Independence: A Principle for Identifiable Disentangled Representations [7.550362088105815]
  Disentangled representations seek to recover latent factors of variation underlying observed data.<n>We introduce a unified framework in which disentanglement is achieved through mechanistic independence.
  arXiv  Detail & Related papers  (2025-09-26T10:58:03Z)
• Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models [30.07172193932125]
  We show that the Joint Autoencoder Modulator (JAM) induces alignment even across independently trained representations.<n>Our findings offer theoretical insight into the structure of shared semantics and practical guidance for transforming generalist unimodal foundations into specialist multimodal models.
  arXiv  Detail & Related papers  (2025-07-01T21:43:50Z)
• Score-based Causal Representation Learning with Interventions [54.735484409244386]
  This paper studies the causal representation learning problem when latent causal variables are observed indirectly. The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
  arXiv  Detail & Related papers  (2023-01-19T18:39:48Z)
• Break The Spell Of Total Correlation In betaTCVAE [4.38301148531795]
  This paper proposes a new iterative decomposition path of total correlation and explains the disentangled representation ability of VAE. The novel model enables VAE to adjust the parameter capacity to divide dependent and independent data features flexibly.
  arXiv  Detail & Related papers  (2022-10-17T07:16:53Z)
• Learning Conditional Invariance through Cycle Consistency [60.85059977904014]
  We propose a novel approach to identify meaningful and independent factors of variation in a dataset. Our method involves two separate latent subspaces for the target property and the remaining input information. We demonstrate on synthetic and molecular data that our approach identifies more meaningful factors which lead to sparser and more interpretable models.
  arXiv  Detail & Related papers  (2021-11-25T17:33:12Z)
• Inference-InfoGAN: Inference Independence via Embedding Orthogonal Basis Expansion [2.198430261120653]
  Disentanglement learning aims to construct independent and interpretable latent variables in which generative models are a popular strategy. We propose a novel GAN-based disentanglement framework via embedding Orthogonal Basis Expansion (OBE) into InfoGAN network. Our Inference-InfoGAN achieves higher disentanglement score in terms of FactorVAE, Separated ferenceAttribute Predictability (SAP), Mutual Information Gap (MIG) and Variation Predictability (VP) metrics without model fine-tuning.
  arXiv  Detail & Related papers  (2021-10-02T11:54:23Z)
• GroupifyVAE: from Group-based Definition to VAE-based Unsupervised Representation Disentanglement [91.9003001845855]
  VAE-based unsupervised disentanglement can not be achieved without introducing other inductive bias. We address VAE-based unsupervised disentanglement by leveraging the constraints derived from the Group Theory based definition as the non-probabilistic inductive bias. We train 1800 models covering the most prominent VAE-based models on five datasets to verify the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-02-20T09:49:51Z)
• Disentangling Observed Causal Effects from Latent Confounders using Method of Moments [67.27068846108047]
  We provide guarantees on identifiability and learnability under mild assumptions. We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
  arXiv  Detail & Related papers  (2021-01-17T07:48:45Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)

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.