Longitudinal Distance: Towards Accountable Instance Attribution

TL;DR

This paper introduces Longitudinal distance, a novel pseudo-metric for attributing instances to neural network decisions, aiming to enhance accountability in interpretable machine learning and explainable AI.

Contribution

The paper proposes a new pseudo-metric called Longitudinal distance for instance attribution, addressing accountability issues in existing interpretability methods.

Findings

Longitudinal distance effectively attributes instances to neural network decisions.

The method enhances accountability in case-based reasoning approaches.

Experimental results demonstrate improved interpretability and accountability.

Abstract

Previous research in interpretable machine learning (IML) and explainable artificial intelligence (XAI) can be broadly categorized as either focusing on seeking interpretability in the agent's model (i.e., IML) or focusing on the context of the user in addition to the model (i.e., XAI). The former can be categorized as feature or instance attribution. Example- or sample-based methods such as those using or inspired by case-based reasoning (CBR) rely on various approaches to select instances that are not necessarily attributing instances responsible for an agent's decision. Furthermore, existing approaches have focused on interpretability and explainability but fall short when it comes to accountability. Inspired in case-based reasoning principles, this paper introduces a pseudo-metric we call Longitudinal distance and its use to attribute instances to a neural network agent's decision that can be potentially used to build accountable CBR agents.