Visual Knowledge Discovery with General Line Coordinates

TL;DR

This paper introduces advanced visual knowledge discovery techniques using General Line Coordinates to improve interpretability and accuracy of linear and non-linear classifiers, facilitating better understanding of complex machine learning models.

Contribution

It extends General Line Coordinates with non-linear, interactive, and worst-case algorithms, enabling more accurate, interpretable models and rules from complex data.

Findings

Method competes with existing algorithms in accuracy and interpretability.

Enables building highly interpretable models from hyperblocks.

Allows analysis of interpretability weaknesses and human-guided discovery.

Abstract

Understanding black-box Machine Learning methods on multidimensional data is a key challenge in Machine Learning. While many powerful Machine Learning methods already exist, these methods are often unexplainable or perform poorly on complex data. This paper proposes visual knowledge discovery approaches based on several forms of lossless General Line Coordinates. These are an expansion of the previously introduced General Line Coordinates Linear and Dynamic Scaffolding Coordinates to produce, explain, and visualize non-linear classifiers with explanation rules. To ensure these non-linear models and rules are accurate, General Line Coordinates Linear also developed new interactive visual knowledge discovery algorithms for finding worst-case validation splits. These expansions are General Line Coordinates non-linear, interactive rules linear, hyperblock rules linear, and worst-case linear. Experiments across multiple benchmark datasets show that this visual knowledge discovery method can compete with other visual and computational Machine Learning algorithms while improving both interpretability and accuracy in linear and non-linear classifications. Major benefits from these expansions consist of the ability to build accurate and highly interpretable models and rules from hyperblocks, the ability to analyze interpretability weaknesses in a model, and the input of expert knowledge through interactive and human-guided visual knowledge discovery methods.