Large Language Models Synergize with Automated Machine Learning

Published: 09 Sept 2024, Last Modified: 17 Sept 2024Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
Abstract: Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a novel form of program synthesis, targeting ML programs, by combining LLMs and automated machine learning (autoML). Specifically, our goal is to fully automate the generation and optimization of the code of the entire ML workflow, from data preparation to modeling and post-processing, utilizing only textual descriptions of the ML tasks. To manage the length and diversity of ML programs, we propose to break each ML program into smaller, manageable parts. Each part is generated separately by the LLM, with careful consideration of their compatibilities. To ensure compatibilities, we design a testing technique for ML programs. Unlike traditional program synthesis, which typically relies on binary evaluations (i.e., correct or incorrect), evaluating ML programs necessitates more than just binary judgments. Our approach automates the numerical evaluation and optimization of these programs, selecting the best candidates through autoML techniques. In experiments across various ML tasks, our method outperforms existing methods in 10 out of 12 tasks for generating ML programs. In addition, autoML significantly improves the performance of the generated ML programs. In experiments, given the textual task description, our method, Text-to-ML, generates the complete and optimized ML program in a fully autonomous process. The implementation of our method is available at https://github.com/JLX0/llm-automl.
Submission Length: Long submission (more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=DEEq5r0k8n
Changes Since Last Submission: We fixed the formatting issue and moved the figure between the title and the abstract to page 2 (now Figure 1)
Code: https://github.com/JLX0/llm-automl
Supplementary Material: zip
Assigned Action Editor: ~Colin_Raffel1
Submission Number: 2684
Loading