Different alloy, different story? Impact of transfer learning on predictive models for in silico screening of Mg dissolution modulators
Citation Link: https://doi.org/10.15480/882.19166
Publikationstyp
Journal Article
Date Issued
2026-09-26
Sprache
English
Author(s)
TORE-DOI
Journal
Volume
273
Issue
C
Article Number
114276
Citation
Corrosion Science 273: 114276 (2026)
Publisher DOI
Publisher
Elsevier
Ideally, datasets for training machine learning models consist of thousands of versatile data samples — a scale that is seldom met in materials research to date. Transfer learning (TL) is widely used to mitigate data scarcity in available training sets by leveraging knowledge from related domains, since models pretrained on auxiliary datasets may learn structure–property relationships that are transferable from one to another. In this work, the potential of TL for predicting the performance of small organic molecule dissolution modulators is probed using corrosion inhibition responses of eleven Mg-based materials taken from the previously published ExCorr database. A significant improvement in prediction accuracy is observed when transfer learning is applied. However, for the dataset configuration studied here, the apparent cross-alloy TL gains are shown not to arise from transferable structure–activity relationship (SAR) knowledge but rather from a learned alloy-context signal embedded in the data. Seven Mg-based materials—six commercial alloys plus the high-purity variant HPMg51—form a shared-SAR cluster with strongly correlated inhibitor rankings, such that molecules labelled on one material are readily predictable for others within the cluster. Within this shared-SAR cluster, extensive overlap reduces the effective training pool from approximately 900 records to only around 180 unique molecules, placing the task firmly in a small-data regime. In this setting, an in-context large language model (Gemini 3.1 Pro) is the only approach that successfully learns meaningful SAR, with its pretrained knowledge providing the transfer that the explicit source dataset fails to deliver.
Seven Mg-based materials in the ExCorr database form a shared-structure–activity relationship (SAR) cluster (pairwise Spearman r=0.67–0.92). Under molecule-disjoint filtering the cross-alloy TL gain on ExCorr splits into a null inhibitor-SAR contribution and a dominant alloy-context contribution. Cross-alloy overlap shrinks ExCorr’s training pool from ≈900records to ≈180unique molecules, only an in-context LLM (Gemini 3.1 Pro) stays predictive.
Seven Mg-based materials in the ExCorr database form a shared-structure–activity relationship (SAR) cluster (pairwise Spearman r=0.67–0.92). Under molecule-disjoint filtering the cross-alloy TL gain on ExCorr splits into a null inhibitor-SAR contribution and a dominant alloy-context contribution. Cross-alloy overlap shrinks ExCorr’s training pool from ≈900records to ≈180unique molecules, only an in-context LLM (Gemini 3.1 Pro) stays predictive.
Subjects
Magnesium corrosion
Inhibition efficiency
Transfer learning
Structure–activity relationships
Machine learning benchmarks
DDC Class
620.1: Engineering Mechanics and Materials Science
006.31: Machine Learning
540: Chemistry
Publication version
publishedVersion