Classification-based detection and quantification of cross-domain data bias in materials discovery

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Trezza, Giovanni, Chiavazzo, Eliodoro
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916977438621696
author Trezza, Giovanni
Chiavazzo, Eliodoro
author_facet Trezza, Giovanni
Chiavazzo, Eliodoro
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09891
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Classification-based detection and quantification of cross-domain data bias in materials discovery
Trezza, Giovanni
Chiavazzo, Eliodoro
Other Condensed Matter
Machine Learning
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.
title Classification-based detection and quantification of cross-domain data bias in materials discovery
topic Other Condensed Matter
Machine Learning
url https://arxiv.org/abs/2311.09891