Unsupervised discovery of the shared and private geometry in multi-view data

ICLR 2026 Conference Submission22494 Authors

Keywords: manifold learning, multi-view, neuroscience, neural network, multi-region

TL;DR: We develop a novel method for learning geometry-preserving representations of shared and private information from multiview data, demonstrating superior interpretability and disentangling than existing methods.

Abstract:

Studying complex real-world phenomena often involves data from multiple views (e.g. sensor modalities or brain regions), each capturing different
aspects of the underlying system. Within neuroscience, there
is growing interest in large-scale simultaneous recordings across multiple
brain regions. Understanding the relationship between views (e.g., the neural
activity in each region recorded) can reveal fundamental insights
into each view and the system as a whole. However, existing methods to
characterize such relationships lack the expressivity required to
capture nonlinear relationships, describe only shared sources
of variance, or discard geometric information
that is crucial to drawing insights from data. Here, we present SPLICE: a neural network-based method that infers disentangled,
interpretable representations of private and shared latent variables from
paired samples of high-dimensional views. Compared to competing methods, we
demonstrate that SPLICE **1)** disentangles shared and private
representations more effectively, **2)** yields more interpretable
representations by preserving geometry, and **3)** is more robust to
incorrect a priori estimates of latent dimensionality. We propose our approach as a general-purpose
method for finding succinct and interpretable descriptions of paired data
sets in terms of disentangled shared and private latent variables.

Primary Area: applications to neuroscience & cognitive science

Submission Number: 22494