Deep Extreme Multi-label Learning

TL;DR

This paper introduces a deep embedding approach for extreme multi-label classification that models label relationships with an explicit graph, effectively handling the vast label space and achieving competitive results.

Contribution

It proposes a novel deep embedding method that combines non-linear embedding with graph-based label space modeling for XML.

Findings

Performs competitively against state-of-the-art methods on public datasets.

Effectively models large label spaces using explicit label graphs.

Demonstrates the practicality of deep learning in extreme multi-label classification.

Abstract

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves $2^L$ possible label sets especially when the label dimension $L$ is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.