Logic-Based Explanations for Linear Support Vector Classifiers with Reject Option


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. Furthermore, although our approach is demonstrated with linear SVCs, it can be easily adapted to other classifiers with reject option, such as neural networks and random forests.
ROCHA, Francisco Mateus; ROCHA, Thiago Alves; RIBEIRO, Reginaldo Pereira Fernandes; ROCHA, Ajalmar Rêgo. Logic-Based Explanations for Linear Support Vector Classifiers with Reject Option. In: BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 12. , 2023, Belo Horizonte/MG. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 144-159. ISSN 2643-6264.