Classification-based detection and quantification of cross-domain data bias in materials discovery
arXiv:2311.09891 · doi:10.1021/acs.jcim.4c01766
Abstract
It stands to reason that the amount and the quality of data is of key importance for setting up accurate AI-driven models. Among others, a fundamental aspect to consider is the bias introduced during sample selection in database generation. This is particularly relevant when a model is trained on a specialized dataset to predict a property of interest, and then applied to forecast the same property over samples having a completely different genesis. Indeed, the resulting biased model will likely produce unreliable predictions for many of those out-of-the-box samples. Neglecting such an aspect may hinder the AI-based discovery process, even when high quality, sufficiently large and highly reputable data sources are available. In this regard, with superconducting and thermoelectric materials as two prototypical case studies in the field of energy material discovery, we present and validate a new method (based on a classification strategy) capable of detecting, quantifying and circumventing the presence of cross-domain data bias.
arXiv comment27 pages, 7 figures (main), 4 figures (supp info)
References in corpus (19)
- Shortcut Learning in Deep Neural Networks
- A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
- Solving high-dimensional partial differential equations using deep learning
- Superconductivity at 250 K in lanthanum hydride under high pressures
- First M87 Event Horizon Telescope Results. IV. Imaging the Central Supermassive Black Hole
- Data-driven materials science: status, challenges and perspectives
- Machine learning modeling of superconducting critical temperature
- Exploration of new superconductors and functional materials and fabrication of superconducting tapes and wires of iron pnictides
- Deep Potential: a general representation of a many-body potential energy surface
- Critical Quantum metrology with a finite-component quantum phase transition
- A critical examination of robustness and generalizability of machine learning prediction of materials properties
- MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
- Deep Learning Model for Finding New Superconductors
- Predicting new superconductors and their critical temperatures using unsupervised machine learning
- Superconducting materials classes: introduction and overview
- Clustering Superconductors Using Unsupervised Machine Learning
- Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
- Leveraging Composition-Based Material Descriptors for Machine Learning Optimization
- Learning effective good variables from physical data