Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019 - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2021

Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019

Zhengying Liu
  • Function : Author
  • PersonId : 1038060
Zhen Xu
  • Function : Author
Rongrong Ji
  • Function : Author
Ge Li
  • Function : Author
Jin Wang
  • Function : Author
Peng Wang
Yang Zhang

Abstract

This paper reports the results and post-challenge analyses of ChaLearn’s AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair comparisons. All input data modalities (time series, images, videos, text, tabular) were formatted as tensors and all tasks were multi-label classification problems. Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly. In this setting, DL methods dominated, though popular Neural Architecture Search (NAS) was impractical. Solutions relied on fine-tuned pre-trained networks, with architectures matching data modality. Post-challenge tests did not reveal improvements beyond the imposed time limit. While no component is particularly original or novel, a high level modular organization emerged featuring a “meta-learner”, “data ingestor”, “model selector”, “model/learner”, and “evaluator”. This modularity enabled ablation studies, which revealed the importance of (off-platform) meta-learning, ensembling, and efficient data management. Experiments on heterogeneous module combinations further confirm the (local) optimality of the winning solutions. Our challenge legacy includes an ever-lasting benchmark (http://autodl.chalearn.org), the open-sourced code of the winners, and a free “AutoDL self-service”.
Fichier principal
Vignette du fichier
TPAMI_AutoDL_paper__draft_version_0022.pdf (1.89 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02957135 , version 1 (04-10-2020)
hal-02957135 , version 2 (30-11-2020)
hal-02957135 , version 3 (06-05-2021)
hal-02957135 , version 4 (01-12-2021)
hal-02957135 , version 5 (08-01-2022)

Identifiers

Cite

Zhengying Liu, Adrien Pavao, Zhen Xu, Sergio Escalera, Fabio Ferreira, et al.. Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, ⟨10.1109/TPAMI.2021.3075372⟩. ⟨hal-02957135v5⟩
408 View
570 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More