teex: a toolbox for the evaluation of explanations
We present teex, a Python toolbox for the evaluation of explanations. teex focuses on the evaluation of local explanations of the predictions of machine learning models by comparing them to ground-truth explanations. It supports several types of explanations: feature importance vectors, saliency map...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2023 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/396241 |
| Acceso en línea: | https://hdl.handle.net/2117/396241 https://dx.doi.org/10.1016/j.neucom.2023.126642 |
| Access Level: | acceso abierto |
| Palabra clave: | Python (Computer program language) Explainable AI Explanation evaluation Python Python (Llenguatge de programació) Àrees temàtiques de la UPC::Informàtica::Llenguatges de programació::Python |
| Sumario: | We present teex, a Python toolbox for the evaluation of explanations. teex focuses on the evaluation of local explanations of the predictions of machine learning models by comparing them to ground-truth explanations. It supports several types of explanations: feature importance vectors, saliency maps, decision rules, and word importance maps. A collection of evaluation metrics is provided for each type. Real-world datasets and generators of synthetic data with ground-truth explanations are also contained within the library. teex contributes to research on explainable AI by providing tested, streamlined, user-friendly tools to compute quality metrics for the evaluation of explanation methods. Source code and a basic overview can be found at github.com/chus-chus/teex, and tutorials and full API documentation are at teex.readthedocs.io. |
|---|