Contextual Local Explanation for Black Box Classifiers

2019/10/02 by Zijian Zhang, Zhang, Zijian, Fan Yang +5
Computer Science · #Anomaly Detection Techniques and Applications #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1910.00768

openalex publication_date 2019/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an interpretable model. We demonstrate the flexibility of CLE by explaining different models for text, tabular and image classification, and the fidelity of it by doing simulated user experiments.

Citations

• Explaining Data-Driven Document Classifications1
• Least angle regression
• ImageNet classification with deep convolutional neural networks
• On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Related

• Interpretable Counterfactual Explanations Guided by Prototypes
• MAIRE -- A Model-Agnostic Interpretable Rule Extraction Procedure for Explaining Classifiers
• Explaining the Predictions of Any Image Classifier via Decision Trees
• Programs as Black-Box Explanations
• Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach