Visualization for Trust in Machine Learning Revisited: The State of the Field in 2023
This survey provides a comprehensive overview for researchers and practitioners in visualization and machine learning, but it is incremental as it builds on prior work.
The authors updated their 2020 survey on visualization techniques for trustworthy machine learning, analyzing 542 techniques as of 2023 to identify trends and eight open challenges, showing a rapid growth in this field over three years.
Visualization for explainable and trustworthy machine learning remains one of the most important and heavily researched fields within information visualization and visual analytics with various application domains, such as medicine, finance, and bioinformatics. After our 2020 state-of-the-art report comprising 200 techniques, we have persistently collected peer-reviewed articles describing visualization techniques, categorized them based on the previously established categorization schema consisting of 119 categories, and provided the resulting collection of 542 techniques in an online survey browser. In this survey article, we present the updated findings of new analyses of this dataset as of fall 2023 and discuss trends, insights, and eight open challenges for using visualizations in machine learning. Our results corroborate the rapidly growing trend of visualization techniques for increasing trust in machine learning models in the past three years, with visualization found to help improve popular model explainability methods and check new deep learning architectures, for instance.