On the Learnability of Multilabel Ranking

Published: 21 Sept 2023, Last Modified: 07 Jan 2024NeurIPS 2023 spotlightEveryoneRevisionsBibTeX
Keywords: Multilabel Ranking, PAC Learning, Online Learning
TL;DR: We give a characterization of learnability for multilabel ranking problems.
Abstract: Multilabel ranking is a central task in machine learning. However, the most fundamental question of learnability in a multilabel ranking setting with relevance-score feedback remains unanswered. In this work, we characterize the learnability of multilabel ranking problems in both batch and online settings for a large family of ranking losses. Along the way, we give two equivalence classes of ranking losses based on learnability that capture most losses used in practice.
Supplementary Material: pdf
Submission Number: 5205