Meta-learning from Learning Curves: Challenge Design and Baseline Results

Nguyen, Manh Hung; Sun-Hosoya, Lisheng; Grinsztajn, Nathan; Guyon, Isabelle

Document type :

Communication dans un congrès avec actes

DOI :

10.1109/IJCNN55064.2022.9892534

Title :

Meta-learning from Learning Curves: Challenge Design and Baseline Results

Author(s) :

Nguyen, Manh Hung [Auteur]
Chalearn
Sun-Hosoya, Lisheng [Auteur]
Chalearn
Grinsztajn, Nathan [Auteur]
Université de Lille
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Guyon, Isabelle [Auteur]
Chalearn
Laboratoire Interdisciplinaire des Sciences du Numérique [LISN]
Université Paris-Saclay
TAckling the Underspecified [TAU]

Conference title :

IJCNN 2022 - International Joint Conference on Neural Networks

City :

Padua

Country :

Italie

Start date of the conference :

2022-07-18

Publisher :

IEEE

English keyword(s) :

AutoML
machine learning
meta-learning
learning curves
learning to learn
reinforcement learning

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

Meta-learning has been widely studied and implemented in many Automated Machine Learning systems to improve the process of selecting and training Machine Learning models for new tasks, by leveraging expertise acquired on ...
Show more >Meta-learning has been widely studied and implemented in many Automated Machine Learning systems to improve the process of selecting and training Machine Learning models for new tasks, by leveraging expertise acquired on previously observed tasks. We design a novel meta-learning challenge aiming at learning-to-learn from one of the most essential model evaluation data, the learning curve. It consists of multiple model evaluations collected during the process of training. A meta-learner is expected to apply a learned policy to learning curves of partially trained models on the task at hand, to rapidly find the best task solution, without training all potential models to convergence. This implies learning the exploration-exploitation trade-off. Our challenge is split into two phases: a development phase and a final test phase. In each phase, a meta-learner is meta-trained and meta-tested on validation learning curves (development phase) or test learning curves (final test phase). During meta-training, the meta-learner is allowed to learn from the provided learning curves in any possible way. In meta-testing, we borrowed the common Reinforcement Learning setting in which an agent (a meta-learner) learns by interacting with an environment storing pre-computed learning curves. A meta-learner must pay a cost (corresponding to the actual training and testing time) to reveal learning curve information progressively. The meta-learner is evaluated and ranked based on the average area under its learning curves. This challenge was accepted as part of the official selection of WCCI 2022 competitions.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Intelligence Artificielle pour Tous

Collections :