The Explabox: Model-Agnostic Machine Learning Transparency & Analysis
This toolkit addresses the need for operationalizing explainability and fairness in ML for model developers and testers, but it is incremental as it builds on existing open-source packages.
The authors tackled the problem of making machine learning models more transparent and responsible by developing the Explabox, an open-source toolkit that provides model-agnostic analyses for explainability, fairness, and robustness, resulting in a tool that transforms complex models and data into interpretable outputs.
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/.