Evolving Counterfactual Explanations with Particle Swarm Optimization and Differential Evolution

Counterfactual explanations are a popular eXplainable AI technique, used to provide contrastive answers to what-if questions. These explanations are consistent with the way that an everyday person will explain an event, and have been shown to satisfy the 'right to explanation' of the European data regulations. Despite this, current work to generate counterfactual explanations either makes assumptions about the model being explained or utlises algorithms that perform suboptimally on continuous data. This work presents two novel algorithms to generate counterfactual explanations using Particle Swarm Optimization (PSO) and Differential Evolution (DE). These are shown to provide effective post-hoc explanations that make no assumptions about the underlying model or data structure. In particular, PSO is shown to generate counterfactual explanations that utilise significantly fewer features to generate sparser explanations when compared to previous related work.

Automated summary

Counterfactual explanations, a popular explainable AI technique, aim to provide contrastive answers to hypothetical questions. This work introduces two novel algorithms, Particle Swarm Optimization (PSO) and Differential Evolution (DE), to generate counterfactual explanations, without assuming anything about the underlying model or data structure. The generated explanations are sparser compared to previous related work.