Design Requirements for Human-Centered Graph Neural Network Explanations
This work tackles the problem of low trust and collaboration barriers in AI for domain experts in fields like social media and drug discovery, but it is incremental as it builds on existing explanation methods.
The paper addresses the challenge of making graph neural network (GNN) predictions interpretable for non-technical domain experts by establishing design requirements for human-centered explanations and demonstrating them with prototypes.
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.