The Explabox: Model-Agnostic Machine Learning Transparency & Analysis

TL;DR

Explabox is an open-source, model-agnostic toolkit designed to enhance transparency, fairness, and robustness in machine learning models through a four-step interpretability process.

Contribution

It introduces a comprehensive, open-source toolkit that operationalizes explainability, fairness, and security assessments for ML models, initially focusing on text data.

Findings

Provides model-agnostic analyses for interpretability and fairness

Supports multiple interaction modes for model evaluation

Enables operationalization of explainability and security practices

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/.