MultiCaM-Vis: Visual Exploration of Multi-Classification Model with High Number of Classes

TL;DR

MultiCaM-Vis is an interactive visual analytics tool designed to explore and diagnose multi-classification models with many classes, aiding experts in identifying root causes of misclassifications.

Contribution

The paper introduces MultiCaM-Vis, a novel visualization tool that handles large numbers of classes using overview+detail views and a Chord diagram, filling a gap in existing solutions.

Findings

Effective in visualizing class-level misclassifications

Supports exploration of large multi-classification models

Preliminary user study shows promising usability

Abstract

Visual exploration of multi-classification models with large number of classes would help machine learning experts in identifying the root cause of a problem that occurs during learning phase such as miss-classification of instances. Most of the previous visual analytics solutions targeted only a few classes. In this paper, we present our interactive visual analytics tool, called MultiCaM-Vis, that provides \Emph{overview+detail} style parallel coordinate views and a Chord diagram for exploration and inspection of class-level miss-classification of instances. We also present results of a preliminary user study with 12 participants.