AutoML-GPT: Automatic Machine Learning with GPT

TL;DR

AutoML-GPT leverages large language models to automate the entire AI training pipeline, including data processing, model selection, and hyperparameter tuning, across diverse tasks and datasets.

Contribution

This paper introduces AutoML-GPT, a novel framework that uses GPT to dynamically automate AI model training and optimization for various tasks, reducing human effort.

Findings

Effective across computer vision and NLP tasks

Automates data processing, model selection, and hyperparameter tuning

Demonstrates robustness and generality through extensive experiments

Abstract

AI tasks encompass a wide range of domains and fields. While numerous AI models have been designed for specific tasks and applications, they often require considerable human efforts in finding the right model architecture, optimization algorithm, and hyperparameters. Recent advances in large language models (LLMs) like ChatGPT show remarkable capabilities in various aspects of reasoning, comprehension, and interaction. Consequently, we propose developing task-oriented prompts and automatically utilizing LLMs to automate the training pipeline. To implement this concept, we present the AutoML-GPT, which employs GPT as the bridge to diverse AI models and dynamically trains models with optimized hyperparameters. AutoML-GPT dynamically takes user requests from the model and data cards and composes the corresponding prompt paragraph. Ultimately, with this prompt paragraph, AutoML-GPT will automatically conduct the experiments from data processing to model architecture, hyperparameter tuning, and predicted training log. By leveraging {\ours}'s robust language capabilities and the available AI models, AutoML-GPT can tackle numerous intricate AI tasks across various tasks and datasets. This approach achieves remarkable results in computer vision, natural language processing, and other challenging areas. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many AI tasks.