Digging into the Landscape of Graphs Counterfactual Explainability (AAAI 2024 Lab)
Laboratory at the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024), February 20–21, 2024, Vancouver, Canada.
In this lab, we provided a hands-on experience to help users develop and evaluate novel Graph Counterfactual Explanation (GCE) methods using a simple and modular framework, GRETEL.
Speakers
- Mario Alfonso Prado-Romero
- Bardh Prenkaj
- Giovanni Stilo
The lab covered foundational concepts in Graph Counterfactual Explainability, practical use of the GRETEL framework for building and benchmarking GCE methods, and hands-on exercises using the SoBigData Research Infrastructure.
Highlights
Based on the ACM Computing Survey: A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges (ACM CSUR, 2024).