An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems

TL;DR

This paper introduces $5$MOEA, an LLM-empowered adaptive evolutionary algorithm designed to improve search efficiency and diversity in multi-component deep learning systems, especially for safety violation detection.

Contribution

It presents the first LLM-empowered adaptive evolutionary algorithm that enhances search performance in multi-component deep learning systems by leveraging LLMs for problem understanding and solution generation.

Findings

$5$MOEA significantly improves search efficiency.

It enhances diversity in evolutionary solutions.

It effectively detects safety violations in MCDL systems.

Abstract

Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $\mu$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $\mu$MOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, $\mu$MOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate $\mu$MOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that $\mu$MOEA can significantly improve the efficiency and diversity of the evolutionary search.