Logic-based Explanations for Linear Support Vector Classifiers with Reject Option
This work addresses the need for interpretability in machine learning models with reject options, which is important for users in high-stakes domains, but it is incremental as it extends existing explanation methods to a specific model variant.
The paper tackles the problem of explaining why a linear support vector classifier with a reject option rejects certain instances, proposing a logic-based method that provides formal guarantees on correctness and minimality. The results show that this method generates shorter explanations with reduced time cost compared to the heuristic Anchors algorithm.
Support Vector Classifier (SVC) is a well-known Machine Learning (ML) model for linear classification problems. It can be used in conjunction with a reject option strategy to reject instances that are hard to correctly classify and delegate them to a specialist. This further increases the confidence of the model. Given this, obtaining an explanation of the cause of rejection is important to not blindly trust the obtained results. While most of the related work has developed means to give such explanations for machine learning models, to the best of our knowledge none have done so for when reject option is present. We propose a logic-based approach with formal guarantees on the correctness and minimality of explanations for linear SVCs with reject option. We evaluate our approach by comparing it to Anchors, which is a heuristic algorithm for generating explanations. Obtained results show that our proposed method gives shorter explanations with reduced time cost.