Obtaining Example-Based Explanations from Deep Neural Networks

TL;DR

This paper introduces EBE-DNN, a method for deriving example-based explanations from deep neural networks by leveraging embeddings and k-nearest neighbors, providing concise, accurate explanations that complement feature attribution.

Contribution

The work presents a novel technique to obtain example-based explanations from deep neural networks using embeddings and k-NN, applicable to complex models beyond traditional methods.

Findings

EBE-DNN provides concentrated example attributions.

Predictions remain accurate with few training examples.

Embedding layer choice significantly affects accuracy.

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 show that EBE-DNN can provide highly concentrated example attributions, i.e., the predictions can be explained with few training examples, without reducing accuracy compared to the original deep neural network. Another important finding from the empirical investigation is that the choice of layer to use for the embeddings may have a large impact on the resulting accuracy.