1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
Realistic Counterfactual Explanations via Denial Constraints
Avia Asael, Nave Frost, Amir Gilad +1
In the realm of Explainable AI, classification results are often explained via counterfactuals (CFs for short), which are (ideally small) perturbations to an instance that lead to…
Measuring Database Unfairness via Dependency Quantification Under Differential Privacy
Mariia Vologdin, Yuchao Tao, Amir Gilad
Differential privacy (DP) has become the de facto standard for protecting sensitive data, providing strong guarantees that published statistics or models reveal limited information…
Analyzing Deviations from Monotonic Trends through Database Repair
Shunit Agmon, Jonathan Gal, Amir Gilad +4
Datasets often exhibit violations of expected monotonic trends - for example, higher education level correlating with higher average salary, newer homes being more expensive, or di…
Finding Convincing Views to Endorse a Claim
Shunit Agmon, Amir Gilad, Brit Youngmann +2
Recent studies investigated the challenge of assessing the strength of a given claim extracted from a dataset, particularly the claim's potential of being misleading and cherry-pic…