Revealing the core dimensions underlying representations in brains, behavior and AI

• URL: http://arxiv.org/abs/2605.26921v1
• Date: Tue, 26 May 2026 12:19:17 GMT
• Title: Revealing the core dimensions underlying representations in brains, behavior and AI
• Abstract summary: Similarity-Based Representation Factorization (SRF) is a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices.<n>Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data.<n>These results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and leveraging the dimensions underlying representations.
• Score: 1.210788495636445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and leveraging the dimensions underlying representations.

Related papers

• Neural network embeddings recover value dimensions from psychometric survey items on par with human data [7.5591367381052175]
  "Survey and Questionnaire Item Embeddings Differentials" (SQuID) is a novel methodological approach that enables neural network embeddings to recover latent dimensions from psychometric survey items.<n>We demonstrate that embeddings derived from large language models, when processed with SQuID, can recover the structure of human values obtained from human rater judgments.
  arXiv  Detail & Related papers  (2025-09-29T15:14:54Z)
• Measuring Orthogonality in Representations of Generative Models [81.13466637365553]
  In unsupervised representation learning, models aim to distill essential features from high-dimensional data into lower-dimensional learned representations. Disentanglement of independent generative processes has long been credited with producing high-quality representations. We propose two novel metrics: Importance-Weighted Orthogonality (IWO) and Importance-Weighted Rank (IWR)
  arXiv  Detail & Related papers  (2024-07-04T08:21:54Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Labeling Neural Representations with Inverse Recognition [25.867702786273586]
  Inverse Recognition (INVERT) is a scalable approach for connecting learned representations with human-understandable concepts. In contrast to prior work, INVERT is capable of handling diverse types of neurons, exhibits less computational complexity, and does not rely on the availability of segmentation masks. We demonstrate the applicability of INVERT in various scenarios, including the identification of representations affected by spurious correlations.
  arXiv  Detail & Related papers  (2023-11-22T18:55:25Z)
• Scalable Regularised Joint Mixture Models [2.0686407686198263]
  In many applications, data can be heterogeneous in the sense of spanning latent groups with different underlying distributions. We propose an approach for heterogeneous data that allows joint learning of (i) explicit multivariate feature distributions, (ii) high-dimensional regression models and (iii) latent group labels. The approach is demonstrably effective in high dimensions, combining data reduction for computational efficiency with a re-weighting scheme that retains key signals even when the number of features is large.
  arXiv  Detail & Related papers  (2022-05-03T13:38:58Z)
• Learning from few examples with nonlinear feature maps [68.8204255655161]
  We explore the phenomenon and reveal key relationships between dimensionality of AI model's feature space, non-degeneracy of data distributions, and the model's generalisation capabilities. The main thrust of our present analysis is on the influence of nonlinear feature transformations mapping original data into higher- and possibly infinite-dimensional spaces on the resulting model's generalisation capabilities.
  arXiv  Detail & Related papers  (2022-03-31T10:36:50Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Efficient Multidimensional Functional Data Analysis Using Marginal Product Basis Systems [2.4554686192257424]
  We propose a framework for learning continuous representations from a sample of multidimensional functional data. We show that the resulting estimation problem can be solved efficiently by the tensor decomposition. We conclude with a real data application in neuroimaging.
  arXiv  Detail & Related papers  (2021-07-30T16:02:15Z)
• A comprehensive comparative evaluation and analysis of Distributional Semantic Models [61.41800660636555]
  We perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT. The results show that the alleged superiority of predict based models is more apparent than real, and surely not ubiquitous. We borrow from cognitive neuroscience the methodology of Representational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models.
  arXiv  Detail & Related papers  (2021-05-20T15:18:06Z)
• Deep Representational Similarity Learning for analyzing neural signatures in task-based fMRI dataset [81.02949933048332]
  This paper develops Deep Representational Similarity Learning (DRSL), a deep extension of Representational Similarity Analysis (RSA) DRSL is appropriate for analyzing similarities between various cognitive tasks in fMRI datasets with a large number of subjects.
  arXiv  Detail & Related papers  (2020-09-28T18:30:14Z)
• Interpretable, similarity-driven multi-view embeddings from high-dimensional biomedical data [0.07031569227782805]
  Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships. SiMLR contributes a novel objective function for identifying joint signal.
  arXiv  Detail & Related papers  (2020-06-11T16:02:22Z)

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.