LeMo-NADe: Multi-Parameter Neural Architecture Discovery with LLMs

TL;DR

LeMo-NADe is a framework that leverages large language models to automatically discover neural network architectures tailored for edge devices, considering multiple user-defined parameters without requiring expert knowledge or predefined search spaces.

Contribution

The paper introduces LeMo-NADe, a novel, user-friendly framework that uses LLMs for multi-parameter neural architecture discovery tailored to edge device constraints.

Findings

Rapid architecture discovery within hours

High-performance models across diverse datasets

Effective consideration of edge-specific parameters

Abstract

Building efficient neural network architectures can be a time-consuming task requiring extensive expert knowledge. This task becomes particularly challenging for edge devices because one has to consider parameters such as power consumption during inferencing, model size, inferencing speed, and CO2 emissions. In this article, we introduce a novel framework designed to automatically discover new neural network architectures based on user-defined parameters, an expert system, and an LLM trained on a large amount of open-domain knowledge. The introduced framework (LeMo-NADe) is tailored to be used by non-AI experts, does not require a predetermined neural architecture search space, and considers a large set of edge device-specific parameters. We implement and validate this proposed neural architecture discovery framework using CIFAR-10, CIFAR-100, and ImageNet16-120 datasets while using GPT-4 Turbo and Gemini as the LLM component. We observe that the proposed framework can rapidly (within hours) discover intricate neural network models that perform extremely well across a diverse set of application settings defined by the user.