Encoding Concepts in Graph Neural Networks. (arXiv:2207.13586v3 [cs.LG] UPDATED)

The opaque reasoning of Graph Neural Networks induces a lack of human trust.
Existing graph network explainers attempt to address this issue by providing
post-hoc explanations, however, they fail to make the model itself more
interpretable. To fill this gap, we introduce the Concept Encoder Module, the
first differentiable concept-discovery approach for graph networks. The
proposed approach makes graph networks explainable by design by first
discovering graph concepts and then using these to solve the task. Our results
demonstrate that …

arxiv encoding graph graph neural networks lg networks neural networks