[2510.22835] Clustering by Denoising: Latent plug-and-play diffusion for single-cell data

Computer Science > Machine Learning arXiv:2510.22835 (cs) [Submitted on 26 Oct 2025 (v1), last revised 2 Mar 2026 (this version, v3)] Title:Clustering by Denoising: Latent plug-and-play diffusion for single-cell data Authors:Dominik Meier, Shixing Yu, Sagnik Nandy, Promit Ghosal, Kyra Gan View a PDF of the paper titled Clustering by Denoising: Latent plug-and-play diffusion for single-cell data, by Dominik Meier and 4 other authors View PDF HTML (experimental) Abstract:Single-cell RNA sequencing (scRNA-seq) enables the study of cellular heterogeneity. Yet, clustering accuracy, and with it downstream analyses based on cell labels, remain challenging due to measurement noise and biological variability. In standard latent spaces (e.g., obtained through PCA), data from different cell types can be projected close together, making accurate clustering difficult. We introduce a latent plug-and-play diffusion framework that separates the observation and denoising space. This separation is operationalized through a novel Gibbs sampling procedure: the learned diffusion prior is applied in a low-dimensional latent space to perform denoising, while to steer this process, noise is reintroduced into the original high-dimensional observation space. This unique "input-space steering" ensures the denoising trajectory remains faithful to the original data structure. Our approach offers three key advantages: (1) adaptive noise handling via a tunable balance between prior and observed data; (2...