Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round

Manh Hung Nguyen (1) , Lisheng Sun (1) , Nathan Grinsztajn (2, 3) , Isabelle Guyon (4, 1, 5)

1 Chalearn
2 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
3 Scool - Scool
4 LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
5 TAU - TAckling the Underspecified

Meta-learning from learning curves is an important yet often neglected research area in the Machine Learning community. We introduce a series of Reinforcement Learning-based meta-learning challenges, in which an agent searches for the best suited algorithm for a given dataset, based on feedback of learning curves from the environment. The first round attracted participants both from academia and industry. This paper analyzes the results of the first round (accepted to the competition program of WCCI 2022), to draw insights into what makes a meta-learner successful at learning from learning curves. With the lessons learned from the first round and the feedback from the participants, we have designed the second round of our challenge with a new protocol and a new meta-dataset. The second round of our challenge is accepted at the AutoML-Conf 2022 and currently ongoing .

Domaines: Intelligence artificielle [cs.AI]

Manh Hung Nguyen, Lisheng Sun, Nathan Grinsztajn, Isabelle Guyon. Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round. 2022. ⟨hal-03725313⟩