239 citations · 695 across the 67 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.LG2023
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
Yi Cai, Gerhard Wunder
Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by uncovering the most influential features in a to-be-explained decisio…
cs.LG2023
Differentially Private Synthetic Data Generation via Lipschitz-Regularised Variational Autoencoders
Benedikt Groß, Gerhard Wunder
Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-l…
cs.CL2023
Explaining text classifiers through progressive neighborhood approximation with realistic samples
Yi Cai, Arthur Zimek, Eirini Ntoutsi +1
The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood…