Toward Scalable and Unified Example-based Explanation and Outlier Detection

TL;DR

This paper introduces a unified approach combining example-based explanations and outlier detection using prototype-based neural networks, enhancing interpretability and anomaly identification without sacrificing accuracy.

Contribution

It proposes a novel prototype replacement algorithm and demonstrates the effectiveness of prototype similarity scores for outlier detection alongside explanation generation.

Findings

Meaningful explanations generated by prototype similarity scores

Effective outlier detection comparable to specialized methods

Maintained classification accuracy while providing interpretability

Abstract

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is important to flag potential outliers for in-depth verification by domain experts. In this work we propose to unify two differing aspects of explainability with outlier detection. We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction and at the same time identify regions of similarity between the predicted sample and the examples. The examples are real prototypical cases sampled from the training set via our novel iterative prototype replacement algorithm. Furthermore, we propose to use the prototype similarity scores for identifying outliers. We compare performances in terms of the classification, explanation quality, and outlier detection of our proposed network with other baselines. We show that our prototype-based networks beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy.