Invited Talk: Graphs' Counterfactual Explainability Landscape (XAI.it 2023)
Invited talk at XAI.it 2023 – 4th Italian Workshop on Explainable Artificial Intelligence, co-located with AIxIA 2023, November 8, 2023, Rome, Italy.
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph akin to the original one, having a different outcome grounded on the underlying predictive model.
During this presentation, Prof. Stilo took the audience on a journey across the GCE landscape, commencing with foundational concepts, introducing the categorization of explainers, emphasizing key tools essential for initiating work in this field, exploring the latest advancements, and concluding with a visual comparison of various generative methods.
Speaker
- Giovanni Stilo