%0 Conference Proceedings
%T How far are we from true AutoML: reflection from winning solutions and results of AutoDL challenge
%A Zhengying Liu
%A Adrien Pavao
%A Zhen Xu
%A Sergio Escalera
%A Isabelle Guyon
%A Julio C. S. Jacques Junior
%A Meysam Madadi
%A Sebastien Treguer
%B 7th ICML Workshop on Automated Machine Learning
%D 2020
%F Zhengying Liu2020
%O HUPBA
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3502), last updated on Tue, 20 Sep 2022 15:22:51 +0200
%X Following the completion of the AutoDL challenge (the final challenge in the ChaLearnAutoDL challenge series 2019), we investigate winning solutions and challenge results toanswer an important motivational question: how far are we from achieving true AutoML?On one hand, the winning solutions achieve good (accurate and fast) classification performance on unseen datasets. On the other hand, all winning solutions still contain aconsiderable amount of hard-coded knowledge on the domain (or modality) such as image,video, text, speech and tabular. This form of ad-hoc meta-learning could be replaced bymore automated forms of meta-learning in the future. Organizing a meta-learning challenge could help forging AutoML solutions that generalize to new unseen domains (e.g.new types of sensor data) as well as gaining insights on the AutoML problem from a morefundamental point of view. The datasets of the AutoDL challenge are a resource that canbe used for further benchmarks and the code of the winners has been outsourced, which isa big step towards “democratizing” Deep Learning.
%U http://refbase.cvc.uab.es/files/LPX2020.pdf