Functionality for Explainable Graph Neural Networks?

[schinto]

Hi!

Are you going to add functionality for the interpretation of GNN models to torchdrug?

There are benchmarks datasets Benchmarks for interpretation of QSAR models and there is a whole bunch of different methods Explainability in Graph Neural Networks: A Taxonomic Survey. Unfortunately, I haven't seen a method which directly combines explainability and uncertainty quantification (like evidential deep learning). That would be really helpful for our medicinal chemists to understand why a decision was made by a model und how certain the model is about the decision.

Thanks

[KiddoZhu]

Hi! We are aware of the importance of explainable models in biomedicine, and we have considered it as a part of our future plan. Unfortunately, due to the limited manpower we have now, such feature may not be realized very soon. Thanks for your understanding.