Visual exploration of machine learning results using data cube analysis

By Minsuk Kahng, Dezhi Fang, Duen Horng Chau. 2016

82 citations recorded by the source corpus.

As complex machine learning systems become more widely adopted, it becomes increasingly challenging for users to understand models or interpret the results generated from the models. We present our ongoing work on developing interactive and visual approaches for exploring and understanding machine learning results using data cube analysis. We propose MLCube, a data cube inspired framework that enables users to define instance subsets using feature conditions and computes aggregate statistics and evaluation metrics over the subsets. We also design MLCube Explorer, an interactive visualization tool for comparing models' performances over the subsets. Users can interactively specify operations, such as drilling down to specific instance subsets, to perform more in-depth exploration. Through a usage scenario, we demonstrate how MLCube Explorer works with a public advertisement click log data set, to help a user build new advertisement click prediction models that advance over an existing model.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Data Lifecycle Challenges in Production Machine Learning (2018, methodology): “For example, MLCube [39] is a tool for visually exploring ML results that enable users to deﬁne slices using feature conditions to compute aggregate statistics and evaluation metrics over the slices.”
Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations (2017, methodology): “Similarly, MLCube Explorer [10] helps users compare model outcomes over various subsets and across multiple models with a data cube analysis type of approach.”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “Manifold [181] and MLCube Explorer [182] are two visual analytical tools that provide comparative analysis for multiple models.”
ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models (2017, methodology): “Slicing results by features helps reveal relationships between data attributes and machine learning algorithms’ outputs [17, 28, 29].”
Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models (2019, methodology): “Example tasks include interactive model debugging and performance analysis [2, 44, 53], feature ideation and selection [6, 34], instance subset inspection and comparison [30, 31], model comparison [67], and constructing interpretable and trustworthy visual analysis systems [11].”
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers (2018, unknown): “While certainly related to model debugging and improvement, model comparison and selection are slightly different tasks in which visualization can be useful [73], [74], [75].”