Overcoming data scarcity with transfer learning
This addresses data scarcity issues in materials science by enabling more accurate models across diverse datasets, though it is incremental as it compares existing transfer learning techniques rather than introducing new ones.
The paper tackles the problem of sparse and inconsistent materials data by comparing three transfer learning architectures, finding that difference architectures work best for mixed DFT and experimental band gaps, multi-task improves classification of color with band gaps, and explicit latent variable methods are most accurate for NO reduction activation energies with error cancellation benefits.
Despite increasing focus on data publication and discovery in materials science and related fields, the global view of materials data is highly sparse. This sparsity encourages training models on the union of multiple datasets, but simple unions can prove problematic as (ostensibly) equivalent properties may be measured or computed differently depending on the data source. These hidden contextual differences introduce irreducible errors into analyses, fundamentally limiting their accuracy. Transfer learning, where information from one dataset is used to inform a model on another, can be an effective tool for bridging sparse data while preserving the contextual differences in the underlying measurements. Here, we describe and compare three techniques for transfer learning: multi-task, difference, and explicit latent variable architectures. We show that difference architectures are most accurate in the multi-fidelity case of mixed DFT and experimental band gaps, while multi-task most improves classification performance of color with band gaps. For activation energies of steps in NO reduction, the explicit latent variable method is not only the most accurate, but also enjoys cancellation of errors in functions that depend on multiple tasks. These results motivate the publication of high quality materials datasets that encode transferable information, independent of industrial or academic interest in the particular labels, and encourage further development and application of transfer learning methods to materials informatics problems.