FeatureNET: Diversity-Driven Generation of Deep Learning Models

Salah Ghamizi, Maxime Cordy, Mike Papadakis, Yves Le Traon

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

3 Citations (Scopus)

Abstract

We present FeatureNET, an open-source Neural Architecture Search (NAS) tool 1 that generates diverse sets of Deep Learning (DL) models. FeatureNET relies on a meta-model of deep neural networks, consisting of generic configurable entities. Then, it uses tools developed in the context of software product lines to generate diverse (maximize the differences between the generated) DL models. The models are translated to Keras and can be integrated into typical machine learning pipelines. FeatureNET allows researchers to generate seamlessly a large variety of models. Thereby, it helps choosing appropriate DL models and performing experiments with diverse models (mitigating potential threats to validity). As a NAS method, FeatureNET successfully generates models performing equally well with handcrafted models.

Original languageEnglish
Title of host publicationProceedings - 2020 ACM/IEEE 42nd International Conference on Software Engineering
Subtitle of host publicationCompanion, ICSE-Companion 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages41-44
Number of pages4
ISBN (Electronic)9781450371223
DOIs
Publication statusPublished - Oct 2020
Externally publishedYes
Event42nd ACM/IEEE International Conference on Software Engineering: Companion, ICSE-Companion 2020 - Seoul, Korea, Republic of
Duration: 27 Jun 202019 Jul 2020

Publication series

NameProceedings - 2020 ACM/IEEE 42nd International Conference on Software Engineering: Companion, ICSE-Companion 2020

Conference

Conference42nd ACM/IEEE International Conference on Software Engineering: Companion, ICSE-Companion 2020
Country/TerritoryKorea, Republic of
CitySeoul
Period27/06/2019/07/20

Keywords

  • AutoML
  • Configuration search
  • NAS
  • Neural Architecture Search

Fingerprint

Dive into the research topics of 'FeatureNET: Diversity-Driven Generation of Deep Learning Models'. Together they form a unique fingerprint.

Cite this