Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution

TL;DR

This paper introduces LEVER, a novel Siamese-style architecture that improves the classification of infrequent labels in extreme classification tasks by reducing label distribution variability and leveraging knowledge transfer.

Contribution

The paper proposes LEVER, a new method that enhances infrequent category classification and introduces two multi-intent datasets for future research.

Findings

Significant performance improvements on multiple XC datasets.

LEVER sets a new benchmark for infrequent label classification.

Introduction of two new multi-intent datasets.

Abstract

This paper presents a novel solution, LEVER, designed to address the challenges posed by underperforming infrequent categories in Extreme Classification (XC) tasks. Infrequent categories, often characterized by sparse samples, suffer from high label inconsistency, which undermines classification performance. LEVER mitigates this problem by adopting a robust Siamese-style architecture, leveraging knowledge transfer to reduce label inconsistency and enhance the performance of One-vs-All classifiers. Comprehensive testing across multiple XC datasets reveals substantial improvements in the handling of infrequent categories, setting a new benchmark for the field. Additionally, the paper introduces two newly created multi-intent datasets, offering essential resources for future XC research.