VA4XDL
State of the Art of Visual Analytics for eXplainable Deep Learning
Biagio La Rosa, Graziano Blasilli, Romain Bourqui, David Auber, Giuseppe Santucci, Roberto Capobianco, Enrico Bertini, Romain Giot, and Marco Angelini. Computer Graphics Forum, 2023. DOI 10.1111/cgf.14733
Open Access Paper
The paper is available at https://doi.org/10.1111/cgf.14733.
Abstract
The use and creation of machine-learning-based solutions to solve problems or reduce their computational costs are becoming increasingly widespread in many domains. Deep Learning plays a large part in this growth. However, it has drawbacks such as a lack of explainability and behaving as a black-box model. During the last few years, Visual Analytics has provided several proposals to cope with these drawbacks, supporting the emerging eXplainable Deep Learning field.
This survey aims to (i) systematically report the contributions of Visual Analytics for eXplainable Deep Learning, (ii) spot gaps and challenges, (iii) serve as an anthology of visual analytical solutions ready to be exploited and put into operation by the Deep Learning community (architects, trainers, and end users), and (iv) prove the degree of maturity, ease of integration, and results for specific domains. The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community.
Citation
@article{LaRosa2023_VA4XDL,
author = {La Rosa, Biagio and Blasilli, Graziano and Bourqui, Romain and Auber, David
and Santucci, Giuseppe and Capobianco, Roberto and Bertini, Enrico
and Giot, Romain and Angelini, Marco},
title = {State of the Art of Visual Analytics for eXplainable Deep Learning},
journal = {Computer Graphics Forum},
volume = {42},
number = {1},
year = {2023},
doi = {10.1111/cgf.14733}
}
Interactive Literature Explorer
This survey collected and categorized a set of 67 papers that propose Visual Analytics solutions for eXplainable Deep Learning. The complete categorization is explorable through SurVis, a web-based interactive explorer, at this link or clicking on the following figure.
Missing Papers
If you have found missing papers in our literature collection, please let us know filling this form.