What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components

TL;DR

This paper presents a modular approach to building customizable explainability tools for machine learning models, emphasizing the importance of interchangeable components for tailored interpretability.

Contribution

It introduces practical training materials and a framework for constructing bespoke surrogate explainers using interoperable algorithmic modules.

Findings

Provides guidance on interpretable representation composition

Details methods for data sampling in explanations

Demonstrates building and evaluating modular explainers

Abstract

Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable. New transparency approaches are developed at breakneck speed, enabling us to peek inside these black boxes and interpret their decisions. Many of these techniques are introduced as monolithic tools, giving the impression of one-size-fits-all and end-to-end algorithms with limited customisability. Nevertheless, such approaches are often composed of multiple interchangeable modules that need to be tuned to the problem at hand to produce meaningful explanations. This paper introduces a collection of hands-on training materials -- slides, video recordings and Jupyter Notebooks -- that provide guidance through the process of building and evaluating bespoke modular surrogate explainers for tabular data. These resources cover the three core building blocks of this technique: interpretable representation composition, data sampling and explanation generation.