DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering

Yuval Heffetz, Roman Vainshtein, Gilad Katz, Lior Rokach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Automatic Machine Learning (AutoML) is an area of research aimed at automating Machine Learning (ML) activities that currently require the involvement of human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architecture used for analysis of previously-unseen data. This task has two challenging aspects: the first is the need to explore a large search space of algorithms and pipeline architectures. The second challenge is the computational cost of training and evaluating multiple pipelines. In this study we present DeepLine, a reinforcement learning-based approach for automatic pipeline generation. Our proposed approach utilizes an efficient representation of the search space together with a novel method for operating in environments with large and dynamic action spaces. By leveraging past knowledge gained from previously-analyzed datasets, our approach only needs to generate and evaluate few dozens of pipelines to reach comparable or better performance than current state-of-the-art AutoML systems that evaluate hundreds and even thousands of pipelines in their optimization process. Evaluation on 56 classification datasets demonstrates the merits of our approach.

Original languageEnglish
Title of host publicationKDD 2020 - Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages2103-2113
Number of pages11
ISBN (Electronic)9781450379984
DOIs
StatePublished - 23 Aug 2020
Event26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020 - Virtual, Online, United States
Duration: 23 Aug 202027 Aug 2020

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020
Country/TerritoryUnited States
CityVirtual, Online
Period23/08/2027/08/20

Keywords

  • AutoML
  • classification
  • deep reinforcement learning

Fingerprint

Dive into the research topics of 'DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering'. Together they form a unique fingerprint.

Cite this