ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems

Abstract

Recently, uncertainty-aware deep learning methods for multiclass labeling problems have been developed that provide calibrated class prediction probabilities and out-of-distribution (OOD) indicators, letting machine learning (ML) consumers and engineers gauge a model's confidence in its predictions. However, this extra neural network prediction information is challenging to scalably convey visually for arbitrary data sources under multiple uncertainty contexts. To address these challenges, we present ScatterUQ, an interactive system that provides targeted visualizations to allow users to better understand model performance in context-driven uncertainty settings. ScatterUQ leverages recent advances in distance-aware neural networks, together with dimensionality reduction techniques, to construct robust, 2-D scatter plots explaining why a model predicts a test example to be (1) in-distribution and of a particular class, (2) in-distribution but unsure of the class, and (3) out-of-distribution. ML consumers and engineers can visually compare the salient features of test samples with training examples through the use of a ``hover callback'' to understand model uncertainty performance and decide follow up courses of action. We demonstrate the effectiveness of ScatterUQ to explain model uncertainty for a multiclass image classification on a distance-aware neural network trained on Fashion-MNIST and tested on Fashion-MNIST (in distribution) and MNIST digits (out of distribution), as well as a deep learning model for a cyber dataset. We quantitatively evaluate dimensionality reduction techniques to optimize our contextually driven UQ visualizations. Our results indicate that the ScatterUQ system should scale to arbitrary, multiclass datasets. Our code is available at https://github.com/mit-ll-responsible-ai/equine-webapp

arXiv comment5 pages, 4 figures, accepted to IEEE VIS 2023

References in corpus (8)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
• Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification
• A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
• DeepLens: Interactive Out-of-distribution Data Detection in NLP Models
• Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection