Inverse Classification for Comparison-based Interpretability in Machine Learning
In the context of post-hoc interpretability, this paper addresses the task of explaining the prediction of a classifier, considering the case where no information is available, neither on the classifier itself, nor on the processed data (neither the training nor the test data). It proposes an instance-based approach whose principle consists in determining the minimal changes needed to alter a prediction: given a data point whose classification must be explained, the proposed method consists in identifying a close neighbour classified differently, where the closeness definition integrates a sparsity constraint. This principle is implemented using observation generation in the Growing Spheres algorithm. Experimental results on two datasets illustrate the relevance of the proposed approach that can be used to gain knowledge about the classifier.
Code (4)
Tasks
BIG-bench Machine LearningClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Enhanced Photonic Chip Design via Interpretable Machine Learning Techniques
Photonic chip design has seen significant advancements with the adoption of inverse design methodologies, offering flexibility and efficiency in optimizing device performance. However, the black-box nature of the optimiz…
Interpretable Machine LearningLearning Optimal Fair Classification Trees: Trade-offs Between Interpretability, Fairness, and Accuracy
The increasing use of machine learning in high-stakes domains -- where people's livelihoods are impacted -- creates an urgent need for interpretable, fair, and highly accurate algorithms. With these needs in mind, we pro…
ClassificationFairnessInverse Design with Dynamic Mode Decomposition
We introduce a computationally efficient method for the automation of inverse design in science and engineering. Based on simple least-square regression, the underlying dynamic mode decomposition algorithm can be used to…
Uncertainty QuantificationInverse Classification with Limited Budget and Maximum Number of Perturbed Samples
Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifiers available, there is a growing need for…
ClassificationGeneral ClassificationFrom hyperplanes to hyperellipsoids: characterizing the inherent interpretability of linear and single-qubit mixed-state binary classification models
We characterize and compare the inherent interpretability offerings of a standard linear model with a single qubit mixed state model for the task of supervised binary classification. A side by side comparison reveals tha…
Quantum Machine LearningBinary ClassificationFeature Importance