xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.
GNNInterpreter: A probabilistic generative model-level explanation for graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
xAI-Drop: Don't Use What You Cannot Explain
xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.