MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices

TL;DR

MONAQ introduces a novel LLM-based multi-objective neural architecture search framework tailored for efficient time-series analysis on resource-limited edge devices, outperforming existing methods in accuracy and efficiency.

Contribution

It pioneers the use of large language models for multi-objective neural architecture querying specifically for time-series analysis on resource-constrained hardware.

Findings

Models discovered by MONAQ outperform handcrafted and NAS baseline models.

MONAQ achieves higher efficiency in model deployment on edge devices.

The framework effectively integrates multimodal data for improved understanding.

Abstract

The growing use of smartphones and IoT devices necessitates efficient time-series analysis on resource-constrained hardware, which is critical for sensing applications such as human activity recognition and air quality prediction. Recent efforts in hardware-aware neural architecture search (NAS) automate architecture discovery for specific platforms; however, none focus on general time-series analysis with edge deployment. Leveraging the problem-solving and reasoning capabilities of large language models (LLM), we propose MONAQ, a novel framework that reformulates NAS into Multi-Objective Neural Architecture Querying tasks. MONAQ is equipped with multimodal query generation for processing multimodal time-series inputs and hardware constraints, alongside an LLM agent-based multi-objective search to achieve deployment-ready models via code generation. By integrating numerical data, time-series images, and textual descriptions, MONAQ improves an LLM's understanding of time-series data. Experiments on fifteen datasets demonstrate that MONAQ-discovered models outperform both handcrafted models and NAS baselines while being more efficient.