Proves universal consistency of GW-k-NN on finite-support metric measure spaces with uniform measure and of fGW-k-NN on node-attributed versions, with competitive empirical performance on graph datasets.
Bioinformatics21 (06 2005)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
AIM is a new evaluation framework for explainability in GNNs that combines accuracy, instance-level, and model-level measures, applied to graph kernel networks to create an improved model xGKN.
An explanation-based detector using seven novel metrics derived from GNN explanations identifies backdoored graphs with high performance on benchmark datasets against multiple attack models.
citing papers explorer
-
Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
An explanation-based detector using seven novel metrics derived from GNN explanations identifies backdoored graphs with high performance on benchmark datasets against multiple attack models.