Saved in:
Bibliographic Details
Main Authors: Raymond, Matt, Saldinger, Jacob Charles, Elvati, Paolo, Scott, Clayton, Violi, Angela
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.14466
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929284793237504
author Raymond, Matt
Saldinger, Jacob Charles
Elvati, Paolo
Scott, Clayton
Violi, Angela
author_facet Raymond, Matt
Saldinger, Jacob Charles
Elvati, Paolo
Scott, Clayton
Violi, Angela
contents Extracting meaningful features from complex, high-dimensional datasets across scientific domains remains challenging. Current methods often struggle with scalability, limiting their applicability to large datasets, or make restrictive assumptions about feature-property relationships, hindering their ability to capture complex interactions. BoUTS's general and scalable feature selection algorithm surpasses these limitations to identify both universal features relevant to all datasets and task-specific features predictive for specific subsets. Evaluated on seven diverse chemical regression datasets, BoUTS achieves state-of-the-art feature sparsity while maintaining prediction accuracy comparable to specialized methods. Notably, BoUTS's universal features enable domain-specific knowledge transfer between datasets, and suggest deep connections in seemingly-disparate chemical datasets. We expect these results to have important repercussions in manually-guided inverse problems. Beyond its current application, BoUTS holds immense potential for elucidating data-poor systems by leveraging information from similar data-rich systems. BoUTS represents a significant leap in cross-domain feature selection, potentially leading to advancements in various scientific fields.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14466
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Universal Feature Selection for Simultaneous Interpretability of Multitask Datasets
Raymond, Matt
Saldinger, Jacob Charles
Elvati, Paolo
Scott, Clayton
Violi, Angela
Machine Learning
Extracting meaningful features from complex, high-dimensional datasets across scientific domains remains challenging. Current methods often struggle with scalability, limiting their applicability to large datasets, or make restrictive assumptions about feature-property relationships, hindering their ability to capture complex interactions. BoUTS's general and scalable feature selection algorithm surpasses these limitations to identify both universal features relevant to all datasets and task-specific features predictive for specific subsets. Evaluated on seven diverse chemical regression datasets, BoUTS achieves state-of-the-art feature sparsity while maintaining prediction accuracy comparable to specialized methods. Notably, BoUTS's universal features enable domain-specific knowledge transfer between datasets, and suggest deep connections in seemingly-disparate chemical datasets. We expect these results to have important repercussions in manually-guided inverse problems. Beyond its current application, BoUTS holds immense potential for elucidating data-poor systems by leveraging information from similar data-rich systems. BoUTS represents a significant leap in cross-domain feature selection, potentially leading to advancements in various scientific fields.
title Universal Feature Selection for Simultaneous Interpretability of Multitask Datasets
topic Machine Learning
url https://arxiv.org/abs/2403.14466