Robust Stochastic Graph Generator for Counterfactual Explanations
This addresses the need for interpretable AI in graph-based domains, offering a generative method for counterfactual explanations, though it appears incremental as it builds on existing generative techniques.
The paper tackles the under-explored problem of generating counterfactual explanations for graphs by introducing RSGG-CE, a robust stochastic graph generator that produces plausible counterfactual examples from a learned latent space, showing improved performance over state-of-the-art generative explainers in quantitative and qualitative analyses.
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the 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 similar to the original one, with a different outcome grounded on the underlying predictive model. Among these 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. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, 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. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates.