Scaling the Explanation of Multi-Class Bayesian Network Classifiers
We propose a new algorithm for compiling Bayesian network classifier (BNC) into class formulas. Class formulas are logical formulas that represent a classifier's input-output behavior, and are crucial in the recent line of work that uses logical reasoning to explain the decisions made by classifiers. Compared to prior work on compiling class formulas of BNCs, our proposed algorithm is not restricted to binary classifiers, shows significant improvement in compilation time, and outputs class formulas as negation normal form (NNF) circuits that are OR-decomposable, which is an important property when computing explanations of classifiers.
Code (0)
등록된 구현이 없습니다.
Tasks
Logical ReasoningSimilar Papers 제목 키워드 기반
A Symbolic Approach to Explaining Bayesian Network Classifiers
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for…
General ClassificationInfluence-Driven Explanations for Bayesian Network Classifiers
One of the most pressing issues in AI in recent years has been the need to address the lack of explainability of many of its models. We focus on explanations for discrete Bayesian network classifiers (BCs), targeting gre…
counterfactualRelationImproving Calibration by Relating Focal Loss, Temperature Scaling, and Properness
Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on t…
image-classificationImage ClassificationPost-Hoc Uncertainty-Aware Explanations for Deployed Power Quality Disturbance Classifiers via Laplace Approximation
Deep learning classifiers achieve high accuracy in power quality disturbance (PQD) recognition, but existing explanation methods return a single deterministic attribution map and provide no measure of its reliability. Th…
Multiple Different Black Box Explanations for Image Classifiers
Existing explanation tools for image classifiers usually give only a single explanation for an image's classification. For many images, however, both humans and image classifiers accept more than one explanation for the …