Research Data and Code for "Auditing Domain Alignment in Latent Representations for Cross-Domain Materials Machine Learning"
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.
Fields of Study & Subjects
Machine Learning in Materials Science
Generative Adversarial Networks and Image Synthesis
Domain Adaptation and Few-Shot Learning
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 January 2026
- Language
- EN