Ching Lam CHOIGradient-based XAI fails to generalise from train to test data: regularisation crucially helps.
Preprint 2023
On the Generalization of Gradient-based Neural Network Interpretations
Related work
ICLR 2025Oral
UNI: Unlearning-based Neural Interpretations
Debiased path attribution by perturbing in the unlearning direction of steepest ascent.