A Disentangled Low-Rank RNN Framework for Uncovering Neural Connectivity and Dynamics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Chengrui, Wang, Yunmiao, Wang, Yule, Li, Weihan, Jaeger, Dieter, Wu, Anqi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917086568120320
author Li, Chengrui
Wang, Yunmiao
Wang, Yule
Li, Weihan
Jaeger, Dieter
Wu, Anqi
author_facet Li, Chengrui
Wang, Yunmiao
Wang, Yule
Li, Weihan
Jaeger, Dieter
Wu, Anqi
contents Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks disentanglement interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Disentangled Recurrent Neural Network (DisRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages disentanglement between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that DisRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage partial disentanglement.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Disentangled Low-Rank RNN Framework for Uncovering Neural Connectivity and Dynamics
Li, Chengrui
Wang, Yunmiao
Wang, Yule
Li, Weihan
Jaeger, Dieter
Wu, Anqi
Neurons and Cognition
Computational Engineering, Finance, and Science
Machine Learning
Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional connectivity is low-rank, it lacks disentanglement interpretations, making it difficult to assign distinct computational roles to different latent dimensions. To address this, we propose the Disentangled Recurrent Neural Network (DisRNN), a generative lrRNN framework that assumes group-wise independence among latent dynamics while allowing flexible within-group entanglement. These independent latent groups allow latent dynamics to evolve separately, but are internally rich for complex computation. We reformulate the lrRNN under a variational autoencoder (VAE) framework, enabling us to introduce a partial correlation penalty that encourages disentanglement between groups of latent dimensions. Experiments on synthetic, monkey M1, and mouse voltage imaging data show that DisRNN consistently improves the disentanglement and interpretability of learned neural latent trajectories in low-dimensional space and low-rank connectivity over baseline lrRNNs that do not encourage partial disentanglement.
title A Disentangled Low-Rank RNN Framework for Uncovering Neural Connectivity and Dynamics
topic Neurons and Cognition
Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2511.13899