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.
Code (1)
Similar Papers 제목 키워드 기반
Robust Explanations for Private Support Vector Machines
We consider counterfactual explanations for private support vector machines (SVM), where the privacy mechanism that publicly releases the classifier guarantees differential privacy. While privacy preservation is essentia…
counterfactualExplainable AI for Classification using Probabilistic Logic Inference
The overarching goal of Explainable AI is to develop systems that not only exhibit intelligent behaviours, but also are able to explain their rationale and reveal insights. In explainable machine learning, methods that p…
ClassificationGeneral ClassificationFast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practice, to derive insights from these models,…
Support Recovery of Sparse Signals from a Mixture of Linear Measurements
Recovery of support of a sparse vector from simple measurements is a widely-studied problem, considered under the frameworks of compressed sensing, 1-bit compressed sensing, and more general single index models. We consi…
compressed sensingDon't Rule Out Simple Models Prematurely: A Large Scale Benchmark Comparing Linear and Non-linear Classifiers in OpenML
A basic step for each data-mining or machine learning task is to determine which model to choose based on the problem and the data at hand. In this paper we investigate when non-linear classifiers outperform linear class…