Towards Automated Evaluation of Explanations in Graph Neural Networks
This work tackles the problem of making GNN explanations more interpretable and evaluable for end users in AI applications, but it appears incremental as it builds on existing trends without claiming major breakthroughs.
The paper addresses the lack of automated evaluation methods for explanations in Graph Neural Networks, proposing new approaches to assess explanations in ways that align with user consumption.
Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose automatic evaluation approaches for GNN Explanations.