LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nasir, Muhammad U., Earle, Sam, Cleghorn, Christopher, James, Steven, Togelius, Julian
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916208645767168
author Nasir, Muhammad U.
Earle, Sam
Cleghorn, Christopher
James, Steven
Togelius, Julian
author_facet Nasir, Muhammad U.
Earle, Sam
Cleghorn, Christopher
James, Steven
Togelius, Julian
contents Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have made a significant impact is in the domain of code generation. Here, we propose using the coding abilities of LLMs to introduce meaningful variations to code defining neural networks. Meanwhile, Quality-Diversity (QD) algorithms are known to discover diverse and robust solutions. By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \texttt{LLMatic}, a Neural Architecture Search (NAS) algorithm. While LLMs struggle to conduct NAS directly through prompts, \texttt{LLMatic} uses a procedural approach, leveraging QD for prompts and network architecture to create diverse and high-performing networks. We test \texttt{LLMatic} on the CIFAR-10 and NAS-bench-201 benchmarks, demonstrating that it can produce competitive networks while evaluating just $2,000$ candidates, even without prior knowledge of the benchmark domain or exposure to any previous top-performing models for the benchmark. The open-sourced code is available in \url{https://github.com/umair-nasir14/LLMatic}.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01102
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
Nasir, Muhammad U.
Earle, Sam
Cleghorn, Christopher
James, Steven
Togelius, Julian
Neural and Evolutionary Computing
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have made a significant impact is in the domain of code generation. Here, we propose using the coding abilities of LLMs to introduce meaningful variations to code defining neural networks. Meanwhile, Quality-Diversity (QD) algorithms are known to discover diverse and robust solutions. By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \texttt{LLMatic}, a Neural Architecture Search (NAS) algorithm. While LLMs struggle to conduct NAS directly through prompts, \texttt{LLMatic} uses a procedural approach, leveraging QD for prompts and network architecture to create diverse and high-performing networks. We test \texttt{LLMatic} on the CIFAR-10 and NAS-bench-201 benchmarks, demonstrating that it can produce competitive networks while evaluating just $2,000$ candidates, even without prior knowledge of the benchmark domain or exposure to any previous top-performing models for the benchmark. The open-sourced code is available in \url{https://github.com/umair-nasir14/LLMatic}.
title LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
topic Neural and Evolutionary Computing
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2306.01102