Enregistré dans:
Détails bibliographiques
Auteurs principaux: Demir, Kaan, Nguyen, Bach, Xue, Bing, Zhang, Mengjie
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.00324
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911768917311488
author Demir, Kaan
Nguyen, Bach
Xue, Bing
Zhang, Mengjie
author_facet Demir, Kaan
Nguyen, Bach
Xue, Bing
Zhang, Mengjie
contents Multi-label loss functions are usually non-differentiable, requiring surrogate loss functions for gradient-based optimisation. The consistency of surrogate loss functions is not proven and is exacerbated by the conflicting nature of multi-label loss functions. To directly learn from multiple related, yet potentially conflicting multi-label loss functions, we propose a Consistent Lebesgue Measure-based Multi-label Learner (CLML) and prove that CLML can achieve theoretical consistency under a Bayes risk framework. Empirical evidence supports our theory by demonstrating that: (1) CLML can consistently achieve state-of-the-art results; (2) the primary performance factor is the Lebesgue measure design, as CLML optimises a simpler feedforward model without additional label graph, perturbation-based conditioning, or semantic embeddings; and (3) an analysis of the results not only distinguishes CLML's effectiveness but also highlights inconsistencies between the surrogate and the desired loss functions.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00324
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Consistent Lebesgue Measure for Multi-label Learning
Demir, Kaan
Nguyen, Bach
Xue, Bing
Zhang, Mengjie
Machine Learning
Multi-label loss functions are usually non-differentiable, requiring surrogate loss functions for gradient-based optimisation. The consistency of surrogate loss functions is not proven and is exacerbated by the conflicting nature of multi-label loss functions. To directly learn from multiple related, yet potentially conflicting multi-label loss functions, we propose a Consistent Lebesgue Measure-based Multi-label Learner (CLML) and prove that CLML can achieve theoretical consistency under a Bayes risk framework. Empirical evidence supports our theory by demonstrating that: (1) CLML can consistently achieve state-of-the-art results; (2) the primary performance factor is the Lebesgue measure design, as CLML optimises a simpler feedforward model without additional label graph, perturbation-based conditioning, or semantic embeddings; and (3) an analysis of the results not only distinguishes CLML's effectiveness but also highlights inconsistencies between the surrogate and the desired loss functions.
title A Consistent Lebesgue Measure for Multi-label Learning
topic Machine Learning
url https://arxiv.org/abs/2402.00324