RECORD
What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components
Machine Learning · Submitted 8 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | 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. | background 1.00 | 0.05 | 0.04 | asserted 0.94 |
| s1 | New transparency approaches are developed at breakneck speed, enabling us to peek inside these black boxes and interpret their decisions. | background 1.00 | 0.06 | 0.03 | asserted 1.00 |
| s2 | 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. | background 0.63 | 0.07 | 0.04 | asserted 0.88 |
| s3 | Nevertheless, such approaches are often composed of multiple interchangeable modules that need to be tuned to the problem at hand to produce meaningful explanations. | background 0.83 | 0.15 | 0.10 | asserted 0.58 |
| s4 | 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. | contribution 1.00 | 0.91 | 0.29 | asserted 1.00 |
| s5 | These resources cover the three core building blocks of this technique: interpretable representation composition, data sampling and explanation generation. | contribution 0.69 | 0.70 | 0.16 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.