Obtaining Example-based Explanations From Deep Neural Networks

Abstract

Most techniques for explainable machine learning focus on feature attribution, i.e., values are assigned to the features such that their sum equals the prediction. Example attribution is another form of explanation that assigns weights to the training examples, such that their scalar product with the labels equals the prediction. The latter may provide valuable complementary information to feature attribution, in particular in cases where the features are not easily interpretable. Current example-based explanation techniques have targeted a few model types only, such as k-nearest neighbors and random forests. In this work, a technique for obtaining example-based explanations from deep neural networks (EBE-DNN) is proposed. The basic idea is to use the deep neural network to obtain an embedding, which is employed by a k-nearest neighbor classifier to form a prediction; the example attribution can hence straightforwardly be derived from the latter. Results from an empirical investigation

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keydong2025obtaining

Related papers

• Generating Explanations To Understand And Repair Embedding-based Entity Alignment (2023)6.34
• Explaining Graph Neural Networks For Node Similarity On Graphs (2024)0.00
• Visual Explanation For Deep Metric Learning (2019)14.36
• Natural Learning (2024)0.00
• Explaining The Success Of Nearest Neighbor Methods In Prediction (2025)18.63
• Visual Explanation Via Similar Feature Activation For Metric Learning (2025)0.00
• A Study On The Interpretability Of Neural Retrieval Models Using Deepshap (2019)13.44
• Towards Visually Explaining Similarity Models (2020)0.00