ICE-SEARCH: A Language Model-Driven Feature Selection Approach

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Tianze, Yang, Tianyi, Lyu, Fuyuan, Liu, Shaoshan, Xue, Liu
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866929337918291968
author	Yang, Tianze Yang, Tianyi Lyu, Fuyuan Liu, Shaoshan Xue Liu
author_facet	Yang, Tianze Yang, Tianyi Lyu, Fuyuan Liu, Shaoshan Xue Liu
contents	This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, which is among the first works that melds large language models (LLMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications. ICE-SEARCH harnesses the crossover and mutation capabilities inherent in LLMs within an evolutionary framework, significantly improving FS through the model's comprehensive world knowledge and its adaptability to a variety of roles. Our evaluation of this methodology spans three crucial MPA tasks: stroke, cardiovascular disease, and diabetes, where ICE-SEARCH outperforms traditional FS methods in pinpointing essential features for medical applications. ICE-SEARCH achieves State-of-the-Art (SOTA) performance in stroke prediction and diabetes prediction; the Decision-Randomized ICE-SEARCH ranks as SOTA in cardiovascular disease prediction. The study emphasizes the critical role of incorporating domain-specific insights, illustrating ICE-SEARCH's robustness, generalizability, and convergence. This opens avenues for further research into comprehensive and intricate FS landscapes, marking a significant stride in the application of artificial intelligence in medical predictive analytics.
format	Preprint
id	arxiv_https___arxiv_org_abs_2402_18609
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	ICE-SEARCH: A Language Model-Driven Feature Selection Approach Yang, Tianze Yang, Tianyi Lyu, Fuyuan Liu, Shaoshan Xue Liu Machine Learning Artificial Intelligence This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, which is among the first works that melds large language models (LLMs) with evolutionary algorithms for feature selection (FS) tasks and demonstrates its effectiveness in Medical Predictive Analytics (MPA) applications. ICE-SEARCH harnesses the crossover and mutation capabilities inherent in LLMs within an evolutionary framework, significantly improving FS through the model's comprehensive world knowledge and its adaptability to a variety of roles. Our evaluation of this methodology spans three crucial MPA tasks: stroke, cardiovascular disease, and diabetes, where ICE-SEARCH outperforms traditional FS methods in pinpointing essential features for medical applications. ICE-SEARCH achieves State-of-the-Art (SOTA) performance in stroke prediction and diabetes prediction; the Decision-Randomized ICE-SEARCH ranks as SOTA in cardiovascular disease prediction. The study emphasizes the critical role of incorporating domain-specific insights, illustrating ICE-SEARCH's robustness, generalizability, and convergence. This opens avenues for further research into comprehensive and intricate FS landscapes, marking a significant stride in the application of artificial intelligence in medical predictive analytics.
title	ICE-SEARCH: A Language Model-Driven Feature Selection Approach
topic	Machine Learning Artificial Intelligence
url	https://arxiv.org/abs/2402.18609