Work

Research Data and Code for "Auditing Domain Alignment in Latent Representations for Cross-Domain Materials Machine Learning"

Year: 2026

Type: article

Abstract: This repository provides a reproducible framework for auditing domain alignment in latent representations learned from heterogeneous materials datasets. The code implements unsupervised latent encoder training, representation-level validation, and quantitative alignment diagnostics independent of predictive accuracy.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.18178230

Author: Enninful, Henry Reynolds Nana Benyin

Institution: Leipzig University

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7119512565

FWCI: 1.438

Cites:

Cited by: 1

Related to: