Propensity-scored Probabilistic Label Trees

TL;DR

This paper introduces an efficient inference method using $A^*$-search for optimal predictions in propensity-scored probabilistic label trees, improving XMLC performance on large, imbalanced label sets.

Contribution

It presents a novel $A^*$-search based inference procedure for probabilistic label trees under the propensity model, enhancing XMLC prediction accuracy.

Findings

Efficiently finds optimal label predictions in XMLC tasks.

Demonstrates improved performance on benchmark datasets.

Validates the approach's effectiveness in real-world scenarios.

Abstract

Extreme multi-label classification (XMLC) refers to the task of tagging instances with small subsets of relevant labels coming from an extremely large set of all possible labels. Recently, XMLC has been widely applied to diverse web applications such as automatic content labeling, online advertising, or recommendation systems. In such environments, label distribution is often highly imbalanced, consisting mostly of very rare tail labels, and relevant labels can be missing. As a remedy to these problems, the propensity model has been introduced and applied within several XMLC algorithms. In this work, we focus on the problem of optimal predictions under this model for probabilistic label trees, a popular approach for XMLC problems. We introduce an inference procedure, based on the $A^*$-search algorithm, that efficiently finds the optimal solution, assuming that all probabilities and propensities are known. We demonstrate the attractiveness of this approach in a wide empirical study on popular XMLC benchmark datasets.