Work

Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?

Year: 2026

Type: preprint

Abstract: In this paper we develop a graph-learning algorithm, MED-MAGMA, to fit multi-axis (Kronecker-sum-structured) models corrupted by multiplicative noise. This type of noise is natural in many application domains, such as that of single-cell RNA sequencing, in which it naturally captures technical biases of RNA sequencing platforms. Our work is evaluated against prior work on each and every public dataset in the Single Cell Expression Atlas under a certain size, demonstrating that our methodology learns networks with better local and global structure. MED-MAGMA is made available as a Python package (MED-MAGMA).

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2603.26327

Authors: Andrew, Bailey, Westhead, David R., Cutillo, Luisa

Institution: University of Leeds

Topic: Single-cell and spatial transcriptomics

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: green

Funders: UK Research and Innovation, National Institute for Health and Care Research, Department of Health and Social Care, Engineering and Physical Sciences Research Council, Leeds Biomedical Research Centre

Awards: G1046889845, G1949475607, UKRI Centre for Doctoral Training in Artificial Intelligence for Medical Diagnosis and Care, G6697820746, G8409589362

OpenAlex ID: W7143365847

Cites:

Cited by:

Related to: