Cost-Sensitive Label Embedding for Multi-Label Classification

TL;DR

This paper introduces CLEMS, a novel cost-sensitive label embedding method for multi-label classification that effectively incorporates various cost functions, improving decision accuracy across different application scenarios.

Contribution

The paper proposes CLEMS, a cost-sensitive label embedding algorithm using multidimensional scaling, capable of handling diverse cost functions and outperforming existing methods.

Findings

CLEMS outperforms existing label embedding algorithms.

CLEMS effectively handles both symmetric and asymmetric cost functions.

Theoretical analysis supports CLEMS's cost-sensitivity capabilities.

Abstract

Label embedding (LE) is an important family of multi-label classification algorithms that digest the label information jointly for better performance. Different real-world applications evaluate performance by different cost functions of interest. Current LE algorithms often aim to optimize one specific cost function, but they can suffer from bad performance with respect to other cost functions. In this paper, we resolve the performance issue by proposing a novel cost-sensitive LE algorithm that takes the cost function of interest into account. The proposed algorithm, cost-sensitive label embedding with multidimensional scaling (CLEMS), approximates the cost information with the distances of the embedded vectors by using the classic multidimensional scaling approach for manifold learning. CLEMS is able to deal with both symmetric and asymmetric cost functions, and effectively makes cost-sensitive decisions by nearest-neighbor decoding within the embedded vectors. We derive theoretical results that justify how CLEMS achieves the desired cost-sensitivity. Furthermore, extensive experimental results demonstrate that CLEMS is significantly better than a wide spectrum of existing LE algorithms and state-of-the-art cost-sensitive algorithms across different cost functions.