A Critical Examination of Active Learning Workflows in Materials Science
This work addresses reliability issues in active learning for materials science practitioners, but it is incremental as it focuses on systematic assessment rather than introducing new methods.
The paper critically examines active learning workflows in materials science, identifying common pitfalls and providing guidance for efficient design and assessment, but does not report specific numerical results.
Active learning (AL) plays a critical role in materials science, enabling applications such as the construction of machine-learning interatomic potentials for atomistic simulations and the operation of self-driving laboratories. Despite its widespread use, the reliability and effectiveness of AL workflows depend on implicit design assumptions that are rarely examined systematically. Here, we critically assess AL workflows deployed in materials science and investigate how key design choices, such as surrogate models, sampling strategies, uncertainty quantification and evaluation metrics, relate to their performance. By identifying common pitfalls and discussing practical mitigation strategies, we provide guidance to practitioners for the efficient design, assessment, and interpretation of AL workflows in materials science.