CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Models

TL;DR

CaBRNet is an open-source, modular framework designed to facilitate the development and evaluation of Case-Based Reasoning models in explainable AI, addressing reproducibility and standardization issues.

Contribution

It introduces a standardized, open-source library for CBR models, improving reproducibility and comparability in explainable AI research.

Findings

Provides a modular framework for CBR models

Enhances reproducibility and standardization in explainable AI

Supports development and evaluation of self-explainable models

Abstract

In the field of explainable AI, a vibrant effort is dedicated to the design of self-explainable models, as a more principled alternative to post-hoc methods that attempt to explain the decisions after a model opaquely makes them. However, this productive line of research suffers from common downsides: lack of reproducibility, unfeasible comparison, diverging standards. In this paper, we propose CaBRNet, an open-source, modular, backward-compatible framework for Case-Based Reasoning Networks: https://github.com/aiser-team/cabrnet.