105 citations
- Monash UniversityAU3 papers
- University of North Carolina at Chapel HillUS3 papers
- The University of Texas at AustinUS2 papers
- Amazon (United States)US1 paper
- Cairo UniversityEG1 paper
- Carnegie Mellon UniversityUS1 paper
- Centro Científico Tecnológico - TucumánAR1 paper
- Coventry (United Kingdom)GB1 paper
- Czech Academy of SciencesCZ1 paper
- Duke UniversityUS1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- EDF Lab Paris-Saclay (France)FR1 paper
4 papers · 1 filter
Efficient Explanations With Relevant Sets
Yacine Izza, Alexey Ignatiev, Nina Narodytska +2
Recent work proposed -relevant inputs (or sets) as a probabilistic explanation for the predictions made by a classifier on a given input. -relevant sets are significant becau…
Explanations for Monotonic Classifiers
Joao Marques-Silva, Thomas Gerspacher, Martin Cooper +2
In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must…
Multicalibrated Partitions for Importance Weights
Parikshit Gopalan, Omer Reingold, Vatsal Sharan +1
The ratio between the probability that two distributions and give to points are known as importance weights or propensity scores and play a fundamental role in many dif…
On Relating 'Why?' and 'Why Not?' Explanations
Alexey Ignatiev, Nina Narodytska, Nicholas Asher +1
Explanations of Machine Learning (ML) models often address a 'Why?' question. Such explanations can be related with selecting feature-value pairs which are sufficient for the predi…