Interpretable Multi-Source Data Fusion Through Latent Variable Gaussian Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ravi, Sandipp Krishnan, Comlek, Yigitcan, Pathak, Arjun, Gupta, Vipul, Umretiya, Rajnikant, Hoffman, Andrew, Pilania, Ghanshyam, Pandita, Piyush, Ghosh, Sayan, Mckeever, Nathaniel, Chen, Wei, Wang, Liping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915023741255680
author Ravi, Sandipp Krishnan
Comlek, Yigitcan
Pathak, Arjun
Gupta, Vipul
Umretiya, Rajnikant
Hoffman, Andrew
Pilania, Ghanshyam
Pandita, Piyush
Ghosh, Sayan
Mckeever, Nathaniel
Chen, Wei
Wang, Liping
author_facet Ravi, Sandipp Krishnan
Comlek, Yigitcan
Pathak, Arjun
Gupta, Vipul
Umretiya, Rajnikant
Hoffman, Andrew
Pilania, Ghanshyam
Pandita, Piyush
Ghosh, Sayan
Mckeever, Nathaniel
Chen, Wei
Wang, Liping
contents With the advent of artificial intelligence and machine learning, various domains of science and engineering communities have leveraged data-driven surrogates to model complex systems through fusing numerous sources of information (data) from published papers, patents, open repositories, or other resources. However, not much attention has been paid to the differences in quality and comprehensiveness of the known and unknown underlying physical parameters of the information sources, which could have downstream implications during system optimization. Additionally, existing methods cannot fuse multi-source data into a single predictive model. Towards resolving this issue, a multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) is proposed. The individual data sources are tagged as a characteristic categorical variable that are mapped into a physically interpretable latent space, allowing the development of source-aware data fusion modeling. Additionally, a dissimilarity metric based on the latent variables of LVGP is introduced to study and understand the differences in the sources of data. The proposed approach is demonstrated on and analyzed through two mathematical and two materials science case studies. From the case studies, it is observed that compared to using single-source and source unaware machine learning models, the proposed multi-source data fusion framework can provide better predictions for sparse-data problems.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interpretable Multi-Source Data Fusion Through Latent Variable Gaussian Process
Ravi, Sandipp Krishnan
Comlek, Yigitcan
Pathak, Arjun
Gupta, Vipul
Umretiya, Rajnikant
Hoffman, Andrew
Pilania, Ghanshyam
Pandita, Piyush
Ghosh, Sayan
Mckeever, Nathaniel
Chen, Wei
Wang, Liping
Machine Learning
With the advent of artificial intelligence and machine learning, various domains of science and engineering communities have leveraged data-driven surrogates to model complex systems through fusing numerous sources of information (data) from published papers, patents, open repositories, or other resources. However, not much attention has been paid to the differences in quality and comprehensiveness of the known and unknown underlying physical parameters of the information sources, which could have downstream implications during system optimization. Additionally, existing methods cannot fuse multi-source data into a single predictive model. Towards resolving this issue, a multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) is proposed. The individual data sources are tagged as a characteristic categorical variable that are mapped into a physically interpretable latent space, allowing the development of source-aware data fusion modeling. Additionally, a dissimilarity metric based on the latent variables of LVGP is introduced to study and understand the differences in the sources of data. The proposed approach is demonstrated on and analyzed through two mathematical and two materials science case studies. From the case studies, it is observed that compared to using single-source and source unaware machine learning models, the proposed multi-source data fusion framework can provide better predictions for sparse-data problems.
title Interpretable Multi-Source Data Fusion Through Latent Variable Gaussian Process
topic Machine Learning
url https://arxiv.org/abs/2402.04146