Label Disentanglement in Partition-based Extreme Multilabel Classification

TL;DR

This paper introduces a novel method for label disentanglement in partition-based extreme multi-label classification, allowing for overlapping clusters that better capture multi-modal labels, resulting in improved accuracy on benchmark datasets.

Contribution

The paper formulates label assignment as an optimization problem and proposes an efficient algorithm for flexible, overlapped label clustering tailored for XMC tasks.

Findings

Achieves state-of-the-art results on four XMC benchmarks.

Effectively disentangles multi-modal labels such as 'Apple' as fruit or brand.

Demonstrates improved precision rates with overlapping label clusters.

Abstract

Partition-based methods are increasingly-used in extreme multi-label classification (XMC) problems due to their scalability to large output spaces (e.g., millions or more). However, existing methods partition the large label space into mutually exclusive clusters, which is sub-optimal when labels have multi-modality and rich semantics. For instance, the label "Apple" can be the fruit or the brand name, which leads to the following research question: can we disentangle these multi-modal labels with non-exclusive clustering tailored for downstream XMC tasks? In this paper, we show that the label assignment problem in partition-based XMC can be formulated as an optimization problem, with the objective of maximizing precision rates. This leads to an efficient algorithm to form flexible and overlapped label clusters, and a method that can alternatively optimizes the cluster assignments and the model parameters for partition-based XMC. Experimental results on synthetic and real datasets show that our method can successfully disentangle multi-modal labels, leading to state-of-the-art (SOTA) results on four XMC benchmarks.