What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components
This work addresses the problem of limited adaptability in explainability tools for researchers and practitioners, but it is incremental as it focuses on educational resources rather than a new method.
The paper tackles the lack of customizability in machine learning explainability tools by introducing hands-on training materials for building modular surrogate explainers for tabular data, covering core components like interpretable representation composition, data sampling, and explanation generation.
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.