English

AlphaD3M: Machine Learning Pipeline Synthesis

Machine Learning 2021-11-05 v1

Abstract

We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play. AlphaD3M is based on edit operations performed over machine learning pipeline primitives providing explainability. We compare AlphaD3M with state-of-the-art AutoML systems: Autosklearn, Autostacker, and TPOT, on OpenML datasets. AlphaD3M achieves competitive performance while being an order of magnitude faster, reducing computation time from hours to minutes, and is explainable by design.

Keywords

Cite

@article{arxiv.2111.02508,
  title  = {AlphaD3M: Machine Learning Pipeline Synthesis},
  author = {Iddo Drori and Yamuna Krishnamurthy and Remi Rampin and Raoni de Paula Lourenco and Jorge Piazentin Ono and Kyunghyun Cho and Claudio Silva and Juliana Freire},
  journal= {arXiv preprint arXiv:2111.02508},
  year   = {2021}
}

Comments

ICML 2018 AutoML Workshop

R2 v1 2026-06-24T07:25:13.059Z