Tag: explainability
All the talks with the tag "explainability".
GNNX-BENCH - Perturbation-based GNN Explainers
Rishi Raj SahooPublished: at 02:00 PMThis work presents a benchmark for Graph Neural Network Explainability with perturbation. This involves some metrics like Sufficiency, Necessity, Stability, and Reproducibility to observe which method performs better. Finally, the work provides recommendations for choosing methods for particular graph tasks.