MLMC: Interactive multi-label multi-classifier evaluation without confusion matrices
This tool addresses the problem of evaluating multi-label classifiers for researchers and practitioners, but it is incremental as it builds on existing visualization methods.
The paper tackles the challenge of evaluating multi-label classifiers by introducing MLMC, a visual exploration tool that provides a scalable alternative to confusion matrices, and a user study demonstrates its effectiveness in enabling powerful evaluation while maintaining user-friendliness.
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.