How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins

TL;DR

This survey explores how twinning neural networks with case-based reasoning systems offers a promising approach for explainable AI, emphasizing post-hoc explanations by example and identifying future research directions.

Contribution

It systematically reviews over 1100 papers on ANN-CBR twins, highlighting their potential as a coherent solution to the XAI problem and mapping future research avenues.

Findings

ANN-CBR twins provide a unified framework for XAI.

The approach has influenced recent deep learning explainability methods.

Future work includes testing feature-weighting and user evaluation techniques.

Abstract

This paper surveys an approach to the XAI problem, using post-hoc explanation by example, that hinges on twinning Artificial Neural Networks (ANNs) with Case-Based Reasoning (CBR) systems, so-called ANN-CBR twins. A systematic survey of 1100+ papers was carried out to identify the fragmented literature on this topic and to trace it influence through to more recent work involving Deep Neural Networks (DNNs). The paper argues that this twin-system approach, especially using ANN-CBR twins, presents one possible coherent, generic solution to the XAI problem (and, indeed, XCBR problem). The paper concludes by road-mapping some future directions for this XAI solution involving (i) further tests of feature-weighting techniques, (iii) explorations of how explanatory cases might best be deployed (e.g., in counterfactuals, near-miss cases, a fortori cases), and (iii) the raising of the unwelcome and, much ignored, issue of human user evaluation.