Poster
in
Affinity Workshop: WiML Workshop 1
Towards Automated Evaluation of Explanations in Graph Neural Networks
Vanya BK · Balaji Ganesan · Devbrat Sharma · Arvind Agarwal
Abstract:
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.
Chat is not available.