Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The Explabox: Model-Agnostic Machine Learning Transparency & Analysis

Marcel Robeer, Michiel Bron, Elize Herrewijnen, Riwish Hoeseni, Floris Bex

TL;DR

The Explabox is an open-source toolkit for transparent and responsible machine learning (ML) model development and usage that empowers model developers and testers to operationalize explainability, fairness, auditability, and security.

Abstract

We present the Explabox: an open-source toolkit for transparent and responsible machine learning (ML) model development and usage. Explabox aids in achieving explainable, fair and robust models by employing a four-step strategy: explore, examine, explain and expose. These steps offer model-agnostic analyses that transform complex 'ingestibles' (models and data) into interpretable 'digestibles'. The toolkit encompasses digestibles for descriptive statistics, performance metrics, model behavior explanations (local and global), and robustness, security, and fairness assessments. Implemented in Python, Explabox supports multiple interaction modes and builds on open-source packages. It empowers model developers and testers to operationalize explainability, fairness, auditability, and security. The initial release focuses on text data and models, with plans for expansion. Explabox's code and documentation are available open-source at https://explabox.readthedocs.io/.

The Explabox: Model-Agnostic Machine Learning Transparency & Analysis

TL;DR

The Explabox is an open-source toolkit for transparent and responsible machine learning (ML) model development and usage that empowers model developers and testers to operationalize explainability, fairness, auditability, and security.

Abstract

We present the Explabox: an open-source toolkit for transparent and responsible machine learning (ML) model development and usage. Explabox aids in achieving explainable, fair and robust models by employing a four-step strategy: explore, examine, explain and expose. These steps offer model-agnostic analyses that transform complex 'ingestibles' (models and data) into interpretable 'digestibles'. The toolkit encompasses digestibles for descriptive statistics, performance metrics, model behavior explanations (local and global), and robustness, security, and fairness assessments. Implemented in Python, Explabox supports multiple interaction modes and builds on open-source packages. It empowers model developers and testers to operationalize explainability, fairness, auditability, and security. The initial release focuses on text data and models, with plans for expansion. Explabox's code and documentation are available open-source at https://explabox.readthedocs.io/.

Paper Structure

This paper contains 11 sections, 1 figure.

Table of Contents

  1. Introduction
  2. The Explabox: Explore, Examine, Explain & Expose your ML models
  3. Ingestibles
  4. Analyses
  5. Explore
  6. Examine
  7. Explain
  8. Expose
  9. Digestibles
  10. Open-source implementation
  11. Conclusion and Future Work

Figures (1)

  • Figure 1: The Explabox facilitates model-agnostic responsible AI development with explainability and versatile analysis tools, accessible through user-friendly interfaces.