Efficient computation of counterfactual explanations of LVQ models
This addresses the need for explainable AI in compliance with regulations like GDPR, focusing on a specific class of models.
The paper tackles the problem of efficiently computing counterfactual explanations for prototype-based classifiers like learning vector quantization models, deriving convex and non-convex programs based on the metric used.
The increasing use of machine learning in practice and legal regulations like EU's GDPR cause the necessity to be able to explain the prediction and behavior of machine learning models. A prominent example of particularly intuitive explanations of AI models in the context of decision making are counterfactual explanations. Yet, it is still an open research problem how to efficiently compute counterfactual explanations for many models. We investigate how to efficiently compute counterfactual explanations for an important class of models, prototype-based classifiers such as learning vector quantization models. In particular, we derive specific convex and non-convex programs depending on the used metric.