Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels

TL;DR

Neo is a visual analytics system that extends confusion matrix visualization to handle hierarchical and multi-output labels, aiding machine learning model evaluation with complex data structures.

Contribution

We introduce an algebraic framework and Neo system for flexible visualization and interaction with advanced confusion matrices in modern machine learning tasks.

Findings

Neo supports hierarchical and multi-output confusion matrices.

Practitioners can better understand complex model performance.

Neo reveals hidden confusions in models.

Abstract

The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances. We conduct formative research with machine learning practitioners at Apple and find that conventional confusion matrices do not support more complex data-structures found in modern-day applications, such as hierarchical and multi-output labels. To express such variations of confusion matrices, we design an algebra that models confusion matrices as probability distributions. Based on this algebra, we develop Neo, a visual analytics system that enables practitioners to flexibly author and interact with hierarchical and multi-output confusion matrices, visualize derived metrics, renormalize confusions, and share matrix specifications. Finally, we demonstrate Neo's utility with three model evaluation scenarios that help people better understand model performance and reveal hidden confusions.