pg_explainer.py #8072
pg_explainer.py
#8072
-
|
How is the connectivity constraint implemented in torch_geometric/explain/algorithm |
Beta Was this translation helpful? Give feedback.
Answered by
wsad1
Sep 26, 2023
Replies: 1 comment 1 reply
-
|
The loss function does not incorporate the connectivity constraint. This is because although the paper mentions connectivity contraints, the implementation in pyg is based on https://github.com/LarsHoldijk/RE-ParameterizedExplainerForGraphNeuralNetworks, which replicated the results in the paper. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
Thanks. |
Beta Was this translation helpful? Give feedback.
Answer selected by
zuluokonkwo
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The loss function does not incorporate the connectivity constraint. This is because although the paper mentions connectivity contraints, the implementation in pyg is based on https://github.com/LarsHoldijk/RE-ParameterizedExplainerForGraphNeuralNetworks, which replicated the results in the paper.