Overcoming data scarcity with transfer learning

Abstract

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.

References in corpus (5)

• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Massively Multitask Networks for Drug Discovery
• ChemTS: An Efficient Python Library for de novo Molecular Generation
• Confidence Intervals for Random Forests: The Jackknife and the Infinitesimal Jackknife
• Fundamental Band Gap and Alignment of Two-Dimensional Semiconductors Explored by Machine Learning

Cited by in corpus (9)

• Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• On-edge Multi-task Transfer Learning: Model and Practice with Data-driven Task Allocation
• AtomSets -- A Hierarchical Transfer Learning Framework for Small and Large Materials Datasets
• MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
• Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
• Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
• Machine learning for impurity charge-state transition levels in semiconductors from elemental properties using multi-fidelity datasets
• AI-Driven Discovery of High Performance Polymer Electrodes for Next-Generation Batteries