Deconfounding to Explanation Evaluation in Graph Neural Networks. (arXiv:2201.08802v1 [cs.LG])

Explainability of graph neural networks (GNNs) aims to answer ``Why the GNN
made a certain prediction?'', which is crucial to interpret the model
prediction. The feature attribution framework distributes a GNN's prediction to
its input features (e.g., edges), identifying an influential subgraph as the
explanation. When evaluating the explanation (i.e., subgraph importance), a
standard way is to audit the model prediction based on the subgraph solely.
However, we argue that a distribution shift exists between the full graph and
the …

arxiv evaluation graph graph neural networks networks neural networks