Multi-Label Feature Selection Using Adaptive and Transformed Relevance

TL;DR

This paper introduces ATR, a novel filter-based multi-label feature selection method that effectively ranks features by considering label-specific and abstract label space information, outperforming existing methods across diverse datasets.

Contribution

The paper proposes ATR, an innovative information-theoretical filter method that combines algorithm adaptation and problem transformation for improved multi-label feature selection.

Findings

ATR outperforms ten state-of-the-art methods across six metrics.

Demonstrates scalability on large feature and label spaces.

Validated on twelve diverse benchmark datasets.

Abstract

Multi-label learning has emerged as a crucial paradigm in data analysis, addressing scenarios where instances are associated with multiple class labels simultaneously. With the growing prevalence of multi-label data across diverse applications, such as text and image classification, the significance of multi-label feature selection has become increasingly evident. This paper presents a novel information-theoretical filter-based multi-label feature selection, called ATR, with a new heuristic function. Incorporating a combinations of algorithm adaptation and problem transformation approaches, ATR ranks features considering individual labels as well as abstract label space discriminative powers. Our experimental studies encompass twelve benchmarks spanning various domains, demonstrating the superiority of our approach over ten state-of-the-art information-theoretical filter-based multi-label feature selection methods across six evaluation metrics. Furthermore, our experiments affirm the scalability of ATR for benchmarks characterized by extensive feature and label spaces. The codes are available at https://github.com/Sadegh28/ATR