Generative Methods for Graph Counterfactual Explanations
Overview
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.
Among GCE techniques, those rooted in generative mechanisms have received relatively limited investigation, despite demonstrating impressive accomplishments in other domains such as artistic styles and natural language modelling.
RSGG-CE (AAAI 2024)
Our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence.
RSGG-CE demonstrates increased abilities in engendering plausible counterfactual candidates compared to state-of-the-art generative explainers.