Design Requirements for Human-Centered Graph Neural Network Explanations

TL;DR

This paper discusses the importance of human-centered explanations for graph neural networks, establishes design requirements to improve interpretability for non-technical users, and demonstrates prototypes embodying these principles.

Contribution

It introduces a set of design requirements for making GNN explanations accessible to domain experts and provides prototype examples to illustrate these principles.

Findings

Identified key design requirements for human-centered GNN explanations

Proposed prototypes demonstrating the application of these requirements

Enhanced interpretability of GNNs for non-technical users

Abstract

Graph neural networks (GNNs) are powerful graph-based machine-learning models that are popular in various domains, e.g., social media, transportation, and drug discovery. However, owing to complex data representations, GNNs do not easily allow for human-intelligible explanations of their predictions, which can decrease trust in them as well as deter any collaboration opportunities between the AI expert and non-technical, domain expert. Here, we first discuss the two papers that aim to provide GNN explanations to domain experts in an accessible manner and then establish a set of design requirements for human-centered GNN explanations. Finally, we offer two example prototypes to demonstrate some of those proposed requirements.