Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hoang, Dung Anh, Nguyen, Cuong, Vasileios, Belagiannis, Do, Thanh-Toan, Carneiro, Gustavo
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912635081981952
author Hoang, Dung Anh
Nguyen, Cuong
Vasileios, Belagiannis
Do, Thanh-Toan
Carneiro, Gustavo
author_facet Hoang, Dung Anh
Nguyen, Cuong
Vasileios, Belagiannis
Do, Thanh-Toan
Carneiro, Gustavo
contents Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced distributed samples. The random selection and manual labelling and balancing of this validation set is not only sub-optimal for meta-learning, but it also scales poorly with the number of classes. Hence, recent meta-learning papers have proposed ad-hoc heuristics to automatically build and label this validation set, but these heuristics are still sub-optimal for meta-learning. In this paper, we analyse the meta-learning algorithm and propose new criteria to characterise the utility of the validation set, based on: 1) the informativeness of the validation set; 2) the class distribution balance of the set; and 3) the correctness of the labels of the set. Furthermore, we propose a new imbalanced noisy-label meta-learning (INOLML) algorithm that automatically builds a validation set by maximising its utility using the criteria above. Our method shows significant improvements over previous meta-learning approaches and sets the new state-of-the-art on several benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2208_08132
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
Hoang, Dung Anh
Nguyen, Cuong
Vasileios, Belagiannis
Do, Thanh-Toan
Carneiro, Gustavo
Machine Learning
Computer Vision and Pattern Recognition
Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced distributed samples. The random selection and manual labelling and balancing of this validation set is not only sub-optimal for meta-learning, but it also scales poorly with the number of classes. Hence, recent meta-learning papers have proposed ad-hoc heuristics to automatically build and label this validation set, but these heuristics are still sub-optimal for meta-learning. In this paper, we analyse the meta-learning algorithm and propose new criteria to characterise the utility of the validation set, based on: 1) the informativeness of the validation set; 2) the class distribution balance of the set; and 3) the correctness of the labels of the set. Furthermore, we propose a new imbalanced noisy-label meta-learning (INOLML) algorithm that automatically builds a validation set by maximising its utility using the criteria above. Our method shows significant improvements over previous meta-learning approaches and sets the new state-of-the-art on several benchmarks.
title Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2208.08132