The rise of machine learning approaches, and in particular deep learning, has led to a significant increase in the performance of AI systems. However, it has also raised the question of the reliability and explicability of their predictions for decision-making (i.e., the black-box issue of the deep models). Such shortcomings also raise many ethical and political concerns that prevent wider adoption of this potentially highly beneficial technology, especially in critical areas, such as healthcare, self-driving cars or security. It is therefore critical to understand how their predictions correlate with information perception and expert decision-making. The objective of eXplainable AI (XAI) is to open this black-box by proposing methods to understand and explain how these systems produce their decisions.

Research work in XAI is currently carried out in parallel by the Machine Learning and the Information Visualization communities using methodologies and competencies from their own field. This special session hosted by the ICPRAI conference, endorsed by IAPR, is an opportunity to fill the gap between Machine Learning and Information Visualization communities and to promote new joint research paths.

Here are the main, but not limited to, topics of interest:

- Trust, Uncertainty, Fairness, Accountability and Transparency
- Explainable/Interpretable Machine Learning
- Information visualization for models or their predictions
- Interactive applications for XAI
- XAI Evaluation and Benchmarks
- Human-AI interface and interaction design
- Sample-centric and Dataset-centric explanations
- Attention mechanisms for XAI
- Pruning with XAI

We expect papers written by researchers from both communities, with a preference for works that imply a joint research (e.g., visualization experts with machine learning experts). Paper selection will be achieved by a program committee of experts in Machine Learning and experts in Information Visualization; additionally, each paper will be reviewed by at least one expert of the two communities.