Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
By Alejandro Barredo Arrieta, Natalia Díaz Rodríguez, Javier Del Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, Salvador Garcia, Sergio Gil-Lopez, Daniel Molina, Richard Benjamins and 2 more. Information Fusion, 2019
9,028 citations recorded by the source corpus.
In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
Subfields: Artificial Intelligence, Health Informatics, Safety, Robustness & Interpretability
View Paper: https://arxiv.org/abs/1910.10045
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Ana Marasovic
- Wojciech Samek
- K. Müller
- Sarah Wiegreffe
- Longo Luca
- Grgoire Montavon
- Percy Liang
In Health Informatics
- Gesina Schwalbe
- Bettina Finzel
- T. Debray
- Jesper C. Provoost
- Ala Al-Fuqaha
- Paul Rad
- Michael J. Muller
- Grgoire Montavon
In Safety, Robustness & Interpretability
- Wojciech Samek
- K. Müller
- Grgoire Montavon
- Longo Luca
- Sebastian Lapuschkin
- Christopher J. Anders
- Klaus‐Robert Müller
- Riccardo Guidotti
Citations in the corpus
- A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “implementations of machine learning models; consider [10], [14]–[18].”
- Mathematical optimization in classification and regression trees (2021, methodology): “To enhance their performance, the greedy procedures were extended in different directions, such as the use of global optimization approaches (Barros et al. 2011; Fu et al. 2003; Grubinger et al. 2014).”
- This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition (2020, background): “Following this demand on understanding automated decision making, explainable Artificial Intelligence (XAI) has been actively researched [1, 3, 18].”
- e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks (2021, background): “They can also enable us to better understand the learned biases of models, and further correct them [5].”
- Artificial intelligence in business: State of the art and future research agenda (2020, methodology): “However, recent AI techniques framed under the eXplainable AI (XAI) algorithms are paving the way for future transparent applications based on AI (Arrieta, 2020).”
- Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: A comprehensive systematic review (2023, background): “This pertains to developing “ responsible and ethical AI ” before it is too late [297,301,302].”