Introduction to Machine Learning Explainability
|An invited lecture offering a high-level introduction to machine learning explainability, given for the Ethics in Computer Science (COMP4920/SENG4920 22T3) course at the University of New South Wales (UNSW), Sydney.|
|Where:||Central Lecture Block, University of New South Wales, Sydney, Australia.|
|When:||12.00–2.00pm on Wednesday, November 16th, 2022.|
Table of Contents
About the Lecture
This lecture offers a high-level introduction to machine learning explainability. It covers topics such as:
- brief history of explainability;
- why we need explainability;
- important developments;
- taxonomy of explainable artificial intelligence;
- what is explainability;
- evaluating explainability;
- examples of explainability; and
- discussion of data explainability, transparent models and post-hoc explainability.
This overview is complemented by a case study of surrogate explainers.
FAT Forensics (Software)
To support the goals of this lecture, I employ
FAT Forensics – an open source Python package
that can inspect selected fairness, accountability and transparency aspects
of data (and their features), models and predictions.
The toolbox spans all of the FAT domains because many of them share underlying
algorithmic components that can be reused in multiple different
implementations, often across the FAT borders.
This interoperability allows, for example, a counterfactual data point
generator to be used as a post-hoc explainer of black-box predictions on
one hand, and as an individual fairness (disparate treatment) inspection tool
on the other.
The modular architecture12 enables
FAT Forensics to deliver robust and tested
low-level FAT building blocks as well as a collection of FAT tools built on top
Users can choose from these ready-made tools or, alternatively, combine the
available building blocks to create their own bespoke algorithms without the
need of modifying the codebase.
The presentation is provided as a collection of (interactive) slides based on reveal.js. The Part I & II slides are created with the reveal.js mode of Quarto. The Case Study slides are created with RISE and offered as a MyST Notebook – a Jupyter Notebook written in Markdown – with embedded iPyWidgets. (See this page for build instructions.) This notebook (hence the presentation) can be executed locally on one’s own machine or launched directly in the web browser through Google Colab or MyBidner.
|Slides||Part I Part II|
|Interactive Case Study||Surrogates|
Kacper is a Research Fellow at the ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S), affiliated with the School of Computing Technologies at RMIT University, Australia; and an Honorary Research Fellow at the Intelligent Systems Laboratory, University of Bristol, United Kingdom.
His main research focus is transparency – interpretability and explainability – of data-driven predictive systems based on artificial intelligence and machine learning algorithms. In particular, he has done work on enhancing transparency of predictive models with feasible and actionable counterfactual explanations and robust modular surrogate explainers. He has also introduced Explainability Fact Sheets – a comprehensive taxonomy of AI and ML explainers – and prototyped Glass-Box – a dialogue-driven interactive explainability system.
Kacper is the designer and lead developer of FAT Forensics – an open source fairness, accountability and transparency Python toolkit. Additionally, he is the main author of a collection of online interactive training materials about machine learning explainability, created in collaboration with the Alan Turing Institute – the UK’s national institute for data science and artificial intelligence.
Kacper holds a Master’s degree in Mathematics and Computer Science, and a doctorate in Computer Science from the University of Bristol, United Kingdom. Prior to joining ADM+S he has held numerous research positions at the University of Bristol, working with projects such as REFrAMe, SPHERE and TAILOR – European Union’s AI Research Excellence Centre. Additionally, he was a visiting researcher at the University of Tartu (Estonia); Simons Institute for the Theory of Computing, UC Berkeley (California, USA); and USI – Università della Svizzera italiana (Lugano, Switzerland). In his research, Kacper collaborated with numerous industry partners, such as THALES, and provided consulting on explainable artificial intelligence and transparent machine learning.
Kacper Sokol, Alexander Hepburn, Rafael Poyiadzi, Matthew Clifford, Raul Santos-Rodriguez, and Peter Flach. 2020. FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems. Journal of Open Source Software, 5(49), p.1904. https://joss.theoj.org/papers/10.21105/joss.01904 ↩
Kacper Sokol, Raul Santos-Rodriguez, and Peter Flach. 2022. FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency. Software Impacts, 14, p.100406. https://doi.org/10.1016/j.simpa.2022.100406 ↩