MLMC: Interactive multi-label multi-classifier evaluation without confusion matrices

TL;DR

MLMC is a visual tool that enables scalable, multi-perspective evaluation of multi-label classifiers, overcoming the limitations of traditional confusion matrices especially in complex, large-scale scenarios.

Contribution

MLMC introduces a novel visualization approach for multi-label classifier evaluation that is scalable and provides multiple performance perspectives.

Findings

MLMC effectively compares classifiers without confusion matrices.

User study confirms MLMC's usability and evaluation power.

Supports analysis from instance, label, and classifier perspectives.

Abstract

Machine learning-based classifiers are commonly evaluated by metrics like accuracy, but deeper analysis is required to understand their strengths and weaknesses. MLMC is a visual exploration tool that tackles the challenge of multi-label classifier comparison and evaluation. It offers a scalable alternative to confusion matrices which are commonly used for such tasks, but don't scale well with a large number of classes or labels. Additionally, MLMC allows users to view classifier performance from an instance perspective, a label perspective, and a classifier perspective. Our user study shows that the techniques implemented by MLMC allow for a powerful multi-label classifier evaluation while preserving user friendliness.