Online Boosting for Multilabel Ranking with Top-k Feedback

TL;DR

This paper introduces online boosting algorithms for multilabel ranking with top-k feedback, using a novel surrogate loss and unbiased estimator to enable learning with limited information, achieving performance close to full information methods.

Contribution

It develops new online boosting algorithms for multilabel ranking under top-k feedback, with theoretical guarantees and practical effectiveness.

Findings

Algorithms perform nearly as well as full information methods.

Theoretical bounds closely match those of full information algorithms.

Experiments show small performance gap between top-k feedback and full information settings.

Abstract

We present online boosting algorithms for multilabel ranking with top-k feedback, where the learner only receives information about the top k items from the ranking it provides. We propose a novel surrogate loss function and unbiased estimator, allowing weak learners to update themselves with limited information. Using these techniques we adapt full information multilabel ranking algorithms (Jung and Tewari, 2018) to the top-k feedback setting and provide theoretical performance bounds which closely match the bounds of their full information counterparts, with the cost of increased sample complexity. These theoretical results are further substantiated by our experiments, which show a small gap in performance between the algorithms for the top-k feedback setting and that for the full information setting across various datasets.