Alibi Explain: Algorithms for Explaining Machine Learning Models

Abstract

We introduce Alibi Explain, an open-source Python library for explaining predictions of machine learning models (https://github.com/SeldonIO/alibi). The library features state-of-the-art explainability algorithms for classification and regression models. The algorithms cover both the model-agnostic (black-box) and model-specific (white-box) setting, cater for multiple data types (tabular, text, images) and explanation scope (local and global explanations). The library exposes a unified API enabling users to work with explanations in a consistent way. Alibi adheres to best development practices featuring extensive testing of code correctness and algorithm convergence in a continuous integration environment. The library comes with extensive documentation of both usage and theoretical background of methods, and a suite of worked end-to-end use cases. Alibi aims to be a production-ready toolkit with integrations into machine learning deployment platforms such as Seldon Core and KFServing, and distributed explanation capabilities using Ray.