Towards AutoML in the presence of Drift: first results

Jorge Madrid 1 Hugo Jair Escalante 1 Eduardo Morales 1 Wei-Wei Tu 2 Yang Yu 3 Lisheng Sun-Hosoya 4, 5 Isabelle Guyon 4, 5 Michèle Sebag 4, 5
5 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Research progress in AutoML has lead to state of the art solutions that can cope quite well with supervised learning task, e.g., classification with AutoSklearn. However, so far these systems do not take into account the changing nature of evolving data over time (i.e., they still assume i.i.d. data); even when this sort of domains are increasingly available in real applications (e.g., spam filtering, user preferences, etc.). We describe a first attempt to develop an AutoML solution for scenarios in which data distribution changes relatively slowly over time and in which the problem is approached in a lifelong learning setting. We extend Auto-Sklearn with sound and intuitive mechanisms that allow it to cope with this sort of problems. The extended Auto-Sklearn is combined with concept drift detection techniques that allow it to automatically determine when the initial models have to be adapted. We report experimental results in benchmark data from AutoML competitions that adhere to this scenario. Results demonstrate the effectiveness of the proposed methodology.
Document type :
Conference papers
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.inria.fr/hal-01966962
Contributor : Marc Schoenauer <>
Submitted on : Sunday, December 30, 2018 - 11:13:03 AM
Last modification on : Thursday, February 7, 2019 - 3:37:19 PM
Long-term archiving on : Sunday, March 31, 2019 - 12:50:38 PM

File

drift-wkpICML2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01966962, version 1

Citation

Jorge Madrid, Hugo Jair Escalante, Eduardo Morales, Wei-Wei Tu, Yang Yu, et al.. Towards AutoML in the presence of Drift: first results. Workshop AutoML 2018 @ ICML/IJCAI-ECAI, Pavel Brazdil, Christophe Giraud-Carrier, and Isabelle Guyon, Jul 2018, Stockholm, Sweden. ⟨hal-01966962⟩

Share

Metrics

Record views

173

Files downloads

549