Papers › Analysis of the AutoML Challenge Series 2015–2018

Analysis of the AutoML Challenge Series 2015–2018

18 May 2019Springer Cham 2019 5archive 2025-07-28

Isabelle Guyon, Lisheng Sun-Hosoya, Marc Boullé, Hugo Jair Escalante, Sergio Escalera, Zhengying Liu, Damir Jajetic, Bisakha Ray, Mehreen Saeed, Michèle Sebag, Alexander Statnikov, WeiWei Tu, Evelyne Viegas

The ChaLearn AutoML Challenge (The authors are in alphabetical order of last name, except the first author who did most of the writing and the second author who produced most of the numerical analyses and plots.) (NIPS 2015 – ICML 2016) consisted of six rounds of a machine learning competition of progressive difficulty, subject to limited computational resources. It was followed by a one-round AutoML challenge (PAKDD 2018). The AutoML setting differs from former model selection/hyper-parameter selection challenges, such as the one we previously organized for NIPS 2006: the participants aim to develop fully automated and computationally efficient systems, capable of being trained and tested without human intervention, with code submission. This chapter analyzes the results of these competitions and provides details about the datasets, which were not revealed to the participants. The solutions of the winners are systematically benchmarked over all datasets of all rounds and compared with canonical machine learning algorithms available in scikit-learn. All materials discussed in this chapter (data and code) have been made publicly available at http://automl.chalearn.org/.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AutoMLBIG-bench Machine LearningModel Selection

Datasets

Introduced by this paper, per the archive.

Chalearn-AutoML-1

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
AutoML Chalearn-AutoML-1 aad_freiburg Duration 5942.22 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Rank (AutoML5) 1.60 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Set1 (F1) 0.7947 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Set2 (PAC) 0.4061 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Set3 (AUC) 0.5543 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Set4 (ABS) 0.2957 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 aad_freiburg Set5 (BAC) 0.5900 #1 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Duration 5842.12 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Rank (AutoML5) 3.00 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Set1 (F1) 0.7531 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Set2 (PAC) 0.3905 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Set3 (AUC) 0.6875 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Set4 (ABS) 0.3067 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 djajetic Set5 (BAC) 0.5517 #2 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Duration 5879.88 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Rank (AutoML5) 4.00 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Set1 (F1) 0.7062 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Set2 (PAC) 0.3708 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Set3 (AUC) 0.5384 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Set4 (ABS) 0.2856 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_ls Set5 (BAC) 0.5580 #3 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Duration 4416.40 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Rank (AutoML5) 4.40 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Set1 (F1) 0.7556 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Set2 (PAC) 0.0343 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Set3 (AUC) 0.2927 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Set4 (ABS) 0.2790 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference Set5 (BAC) 0.5601 #4 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Duration 4353.45 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Rank (AutoML5) 4.60 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Set1 (F1) 0.7565 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Set2 (PAC) 0.0172 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Set3 (AUC) 0.2911 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Set4 (ABS) 0.2791 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 abhishek4 Set5 (BAC) 0.5595 #5 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Duration 3343.64 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Rank (AutoML5) 5.20 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Set1 (F1) 0.7542 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Set2 (PAC) 0.2802 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Set3 (AUC) 0.3333 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Set4 (ABS) 0.1507 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 postech.mlg_exbrain Set5 (BAC) 0.5564 #6 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Duration 4889.14 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Rank (AutoML5) 5.20 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Set1 (F1) 0.7005 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Set2 (PAC) 0.3698 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Set3 (AUC) 0.6776 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Set4 (ABS) 0.2507 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 reference_mb Set5 (BAC) 0.4618 #7 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Duration 4603.81 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Rank (AutoML5) 6.40 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Set1 (F1) 0.7005 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Set2 (PAC) 0.3698 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Set3 (AUC) -1.0000 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Set4 (ABS) 0.2507 #8 of 8 Archive leaderboard report
AutoML Chalearn-AutoML-1 marc.boulle Set5 (BAC) 0.4618 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections